1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
|
<html><body>
<style>
body, h1, h2, h3, div, span, p, pre, a {
margin: 0;
padding: 0;
border: 0;
font-weight: inherit;
font-style: inherit;
font-size: 100%;
font-family: inherit;
vertical-align: baseline;
}
body {
font-size: 13px;
padding: 1em;
}
h1 {
font-size: 26px;
margin-bottom: 1em;
}
h2 {
font-size: 24px;
margin-bottom: 1em;
}
h3 {
font-size: 20px;
margin-bottom: 1em;
margin-top: 1em;
}
pre, code {
line-height: 1.5;
font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}
pre {
margin-top: 0.5em;
}
h1, h2, h3, p {
font-family: Arial, sans serif;
}
h1, h2, h3 {
border-bottom: solid #CCC 1px;
}
.toc_element {
margin-top: 0.5em;
}
.firstline {
margin-left: 2 em;
}
.method {
margin-top: 1em;
border: solid 1px #CCC;
padding: 1em;
background: #EEE;
}
.details {
font-weight: bold;
font-size: 14px;
}
</style>
<h1><a href="documentai_v1beta3.html">Cloud Document AI API</a> . <a href="documentai_v1beta3.projects.html">projects</a> . <a href="documentai_v1beta3.projects.locations.html">locations</a> . <a href="documentai_v1beta3.projects.locations.processors.html">processors</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
<code><a href="documentai_v1beta3.projects.locations.processors.humanReviewConfig.html">humanReviewConfig()</a></code>
</p>
<p class="firstline">Returns the humanReviewConfig Resource.</p>
<p class="toc_element">
<code><a href="documentai_v1beta3.projects.locations.processors.processorVersions.html">processorVersions()</a></code>
</p>
<p class="firstline">Returns the processorVersions Resource.</p>
<p class="toc_element">
<code><a href="#batchProcess">batchProcess(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">LRO endpoint to batch process many documents. The output is written to Cloud Storage as JSON in the [Document] format.</p>
<p class="toc_element">
<code><a href="#close">close()</a></code></p>
<p class="firstline">Close httplib2 connections.</p>
<p class="toc_element">
<code><a href="#create">create(parent, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Creates a processor from the type processor that the user chose. The processor will be at "ENABLED" state by default after its creation.</p>
<p class="toc_element">
<code><a href="#delete">delete(name, x__xgafv=None)</a></code></p>
<p class="firstline">Deletes the processor, unloads all deployed model artifacts if it was enabled and then deletes all artifacts associated with this processor.</p>
<p class="toc_element">
<code><a href="#disable">disable(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Disables a processor</p>
<p class="toc_element">
<code><a href="#enable">enable(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Enables a processor</p>
<p class="toc_element">
<code><a href="#get">get(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets a processor detail.</p>
<p class="toc_element">
<code><a href="#list">list(parent, pageSize=None, pageToken=None, x__xgafv=None)</a></code></p>
<p class="firstline">Lists all processors which belong to this project.</p>
<p class="toc_element">
<code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>
<p class="firstline">Retrieves the next page of results.</p>
<p class="toc_element">
<code><a href="#process">process(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Processes a single document.</p>
<p class="toc_element">
<code><a href="#setDefaultProcessorVersion">setDefaultProcessorVersion(processor, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Set the default (active) version of a Processor that will be used in ProcessDocument and BatchProcessDocuments.</p>
<h3>Method Details</h3>
<div class="method">
<code class="details" id="batchProcess">batchProcess(name, body=None, x__xgafv=None)</code>
<pre>LRO endpoint to batch process many documents. The output is written to Cloud Storage as JSON in the [Document] format.
Args:
name: string, Required. The resource name of Processor or ProcessorVersion. Format: projects/{project}/locations/{location}/processors/{processor}, or projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion} (required)
body: object, The request body.
The object takes the form of:
{ # Request message for batch process document method.
"documentOutputConfig": { # Config that controls the output of documents. All documents will be written as a JSON file. # The overall output config for batch process.
"gcsOutputConfig": { # The configuration used when outputting documents. # Output config to write the results to Cloud Storage.
"gcsUri": "A String", # The Cloud Storage uri (a directory) of the output.
},
},
"inputConfigs": [ # The input config for each single document in the batch process.
{ # The message for input config in batch process.
"gcsSource": "A String", # The Cloud Storage location as the source of the document.
"mimeType": "A String", # Mimetype of the input. If the input is a raw document, the supported mimetypes are application/pdf, image/tiff, and image/gif. If the input is a [Document] proto, the type should be application/json.
},
],
"inputDocuments": { # The common config to specify a set of documents used as input. # The input documents for batch process.
"gcsDocuments": { # Specifies a set of documents on Cloud Storage. # The set of documents individually specified on Cloud Storage.
"documents": [ # The list of documents.
{ # Specifies a document stored on Cloud Storage.
"gcsUri": "A String", # The Cloud Storage object uri.
"mimeType": "A String", # An IANA MIME type (RFC6838) of the content.
},
],
},
"gcsPrefix": { # Specifies all documents on Cloud Storage with a common prefix. # The set of documents that match the specified Cloud Storage [gcs_prefix].
"gcsUriPrefix": "A String", # The URI prefix.
},
},
"outputConfig": { # The message for output config in batch process. # The overall output config for batch process.
"gcsDestination": "A String", # The output Cloud Storage directory to put the processed documents.
},
"skipHumanReview": True or False, # Whether Human Review feature should be skipped for this request. Default to false.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="close">close()</code>
<pre>Close httplib2 connections.</pre>
</div>
<div class="method">
<code class="details" id="create">create(parent, body=None, x__xgafv=None)</code>
<pre>Creates a processor from the type processor that the user chose. The processor will be at "ENABLED" state by default after its creation.
Args:
parent: string, Required. The parent (project and location) under which to create the processor. Format: projects/{project}/locations/{location} (required)
body: object, The request body.
The object takes the form of:
{ # The first-class citizen for DAI. Each processor defines how to extract structural information from a document.
"createTime": "A String", # The time the processor was created.
"defaultProcessorVersion": "A String", # The default processor version.
"displayName": "A String", # The display name of the processor.
"kmsKeyName": "A String", # The KMS key used for encryption/decryption in CMEK scenarios. See https://cloud.google.com/security-key-management.
"name": "A String", # Output only. Immutable. The resource name of the processor. Format: projects/{project}/locations/{location}/processors/{processor}
"processEndpoint": "A String", # Output only. Immutable. The http endpoint that can be called to invoke processing.
"state": "A String", # Output only. The state of the processor.
"type": "A String", # The processor type, e.g., INVOICE_PARSING, W2_PARSING, etc.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # The first-class citizen for DAI. Each processor defines how to extract structural information from a document.
"createTime": "A String", # The time the processor was created.
"defaultProcessorVersion": "A String", # The default processor version.
"displayName": "A String", # The display name of the processor.
"kmsKeyName": "A String", # The KMS key used for encryption/decryption in CMEK scenarios. See https://cloud.google.com/security-key-management.
"name": "A String", # Output only. Immutable. The resource name of the processor. Format: projects/{project}/locations/{location}/processors/{processor}
"processEndpoint": "A String", # Output only. Immutable. The http endpoint that can be called to invoke processing.
"state": "A String", # Output only. The state of the processor.
"type": "A String", # The processor type, e.g., INVOICE_PARSING, W2_PARSING, etc.
}</pre>
</div>
<div class="method">
<code class="details" id="delete">delete(name, x__xgafv=None)</code>
<pre>Deletes the processor, unloads all deployed model artifacts if it was enabled and then deletes all artifacts associated with this processor.
Args:
name: string, Required. The processor resource name to be deleted. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="disable">disable(name, body=None, x__xgafv=None)</code>
<pre>Disables a processor
Args:
name: string, Required. The processor resource name to be disabled. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for the disable processor method.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="enable">enable(name, body=None, x__xgafv=None)</code>
<pre>Enables a processor
Args:
name: string, Required. The processor resource name to be enabled. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for the enable processor method.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="get">get(name, x__xgafv=None)</code>
<pre>Gets a processor detail.
Args:
name: string, Required. The processor resource name. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # The first-class citizen for DAI. Each processor defines how to extract structural information from a document.
"createTime": "A String", # The time the processor was created.
"defaultProcessorVersion": "A String", # The default processor version.
"displayName": "A String", # The display name of the processor.
"kmsKeyName": "A String", # The KMS key used for encryption/decryption in CMEK scenarios. See https://cloud.google.com/security-key-management.
"name": "A String", # Output only. Immutable. The resource name of the processor. Format: projects/{project}/locations/{location}/processors/{processor}
"processEndpoint": "A String", # Output only. Immutable. The http endpoint that can be called to invoke processing.
"state": "A String", # Output only. The state of the processor.
"type": "A String", # The processor type, e.g., INVOICE_PARSING, W2_PARSING, etc.
}</pre>
</div>
<div class="method">
<code class="details" id="list">list(parent, pageSize=None, pageToken=None, x__xgafv=None)</code>
<pre>Lists all processors which belong to this project.
Args:
parent: string, Required. The parent (project and location) which owns this collection of Processors. Format: projects/{project}/locations/{location} (required)
pageSize: integer, The maximum number of processors to return. If unspecified, at most 50 processors will be returned. The maximum value is 100; values above 100 will be coerced to 100.
pageToken: string, We will return the processors sorted by creation time. The page token will point to the next processor.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for list processors.
"nextPageToken": "A String", # Points to the next processor, otherwise empty.
"processors": [ # The list of processors.
{ # The first-class citizen for DAI. Each processor defines how to extract structural information from a document.
"createTime": "A String", # The time the processor was created.
"defaultProcessorVersion": "A String", # The default processor version.
"displayName": "A String", # The display name of the processor.
"kmsKeyName": "A String", # The KMS key used for encryption/decryption in CMEK scenarios. See https://cloud.google.com/security-key-management.
"name": "A String", # Output only. Immutable. The resource name of the processor. Format: projects/{project}/locations/{location}/processors/{processor}
"processEndpoint": "A String", # Output only. Immutable. The http endpoint that can be called to invoke processing.
"state": "A String", # Output only. The state of the processor.
"type": "A String", # The processor type, e.g., INVOICE_PARSING, W2_PARSING, etc.
},
],
}</pre>
</div>
<div class="method">
<code class="details" id="list_next">list_next(previous_request, previous_response)</code>
<pre>Retrieves the next page of results.
Args:
previous_request: The request for the previous page. (required)
previous_response: The response from the request for the previous page. (required)
Returns:
A request object that you can call 'execute()' on to request the next
page. Returns None if there are no more items in the collection.
</pre>
</div>
<div class="method">
<code class="details" id="process">process(name, body=None, x__xgafv=None)</code>
<pre>Processes a single document.
Args:
name: string, Required. The resource name of the Processor or ProcessorVersion to use for processing. If a Processor is specified, the server will use its default version. Format: projects/{project}/locations/{location}/processors/{processor}, or projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion} (required)
body: object, The request body.
The object takes the form of:
{ # Request message for the process document method.
"document": { # Document represents the canonical document resource in Document Understanding AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document Understanding AI to iterate and optimize for quality. # The document payload, the [content] and [mime_type] fields must be set.
"content": "A String", # Optional. Inline document content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.
"entities": [ # A list of entities detected on Document.text. For document shards, entities in this list may cross shard boundaries.
{ # An entity that could be a phrase in the text or a property belongs to the document. It is a known entity type, such as a person, an organization, or location.
"confidence": 3.14, # Optional. Confidence of detected Schema entity. Range [0, 1].
"id": "A String", # Optional. Canonical id. This will be a unique value in the entity list for this document.
"mentionId": "A String", # Optional. Deprecated. Use `id` field instead.
"mentionText": "A String", # Optional. Text value in the document e.g. `1600 Amphitheatre Pkwy`. If the entity is not present in the document, this field will be empty.
"normalizedValue": { # Parsed and normalized entity value. # Optional. Normalized entity value. Absent if the extracted value could not be converted or the type (e.g. address) is not supported for certain parsers. This field is also only populated for certain supported document types.
"addressValue": { # Represents a postal address, e.g. for postal delivery or payments addresses. Given a postal address, a postal service can deliver items to a premise, P.O. Box or similar. It is not intended to model geographical locations (roads, towns, mountains). In typical usage an address would be created via user input or from importing existing data, depending on the type of process. Advice on address input / editing: - Use an i18n-ready address widget such as https://github.com/google/libaddressinput) - Users should not be presented with UI elements for input or editing of fields outside countries where that field is used. For more guidance on how to use this schema, please see: https://support.google.com/business/answer/6397478 # Postal address. See also: https://github.com/googleapis/googleapis/blob/master/google/type/postal_address.proto
"addressLines": [ # Unstructured address lines describing the lower levels of an address. Because values in address_lines do not have type information and may sometimes contain multiple values in a single field (e.g. "Austin, TX"), it is important that the line order is clear. The order of address lines should be "envelope order" for the country/region of the address. In places where this can vary (e.g. Japan), address_language is used to make it explicit (e.g. "ja" for large-to-small ordering and "ja-Latn" or "en" for small-to-large). This way, the most specific line of an address can be selected based on the language. The minimum permitted structural representation of an address consists of a region_code with all remaining information placed in the address_lines. It would be possible to format such an address very approximately without geocoding, but no semantic reasoning could be made about any of the address components until it was at least partially resolved. Creating an address only containing a region_code and address_lines, and then geocoding is the recommended way to handle completely unstructured addresses (as opposed to guessing which parts of the address should be localities or administrative areas).
"A String",
],
"administrativeArea": "A String", # Optional. Highest administrative subdivision which is used for postal addresses of a country or region. For example, this can be a state, a province, an oblast, or a prefecture. Specifically, for Spain this is the province and not the autonomous community (e.g. "Barcelona" and not "Catalonia"). Many countries don't use an administrative area in postal addresses. E.g. in Switzerland this should be left unpopulated.
"languageCode": "A String", # Optional. BCP-47 language code of the contents of this address (if known). This is often the UI language of the input form or is expected to match one of the languages used in the address' country/region, or their transliterated equivalents. This can affect formatting in certain countries, but is not critical to the correctness of the data and will never affect any validation or other non-formatting related operations. If this value is not known, it should be omitted (rather than specifying a possibly incorrect default). Examples: "zh-Hant", "ja", "ja-Latn", "en".
"locality": "A String", # Optional. Generally refers to the city/town portion of the address. Examples: US city, IT comune, UK post town. In regions of the world where localities are not well defined or do not fit into this structure well, leave locality empty and use address_lines.
"organization": "A String", # Optional. The name of the organization at the address.
"postalCode": "A String", # Optional. Postal code of the address. Not all countries use or require postal codes to be present, but where they are used, they may trigger additional validation with other parts of the address (e.g. state/zip validation in the U.S.A.).
"recipients": [ # Optional. The recipient at the address. This field may, under certain circumstances, contain multiline information. For example, it might contain "care of" information.
"A String",
],
"regionCode": "A String", # Required. CLDR region code of the country/region of the address. This is never inferred and it is up to the user to ensure the value is correct. See http://cldr.unicode.org/ and http://www.unicode.org/cldr/charts/30/supplemental/territory_information.html for details. Example: "CH" for Switzerland.
"revision": 42, # The schema revision of the `PostalAddress`. This must be set to 0, which is the latest revision. All new revisions **must** be backward compatible with old revisions.
"sortingCode": "A String", # Optional. Additional, country-specific, sorting code. This is not used in most regions. Where it is used, the value is either a string like "CEDEX", optionally followed by a number (e.g. "CEDEX 7"), or just a number alone, representing the "sector code" (Jamaica), "delivery area indicator" (Malawi) or "post office indicator" (e.g. Côte d'Ivoire).
"sublocality": "A String", # Optional. Sublocality of the address. For example, this can be neighborhoods, boroughs, districts.
},
"booleanValue": True or False, # Boolean value. Can be used for entities with binary values, or for checkboxes.
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values * A month and day value, with a zero year, such as an anniversary * A year on its own, with zero month and day values * A year and month value, with a zero day, such as a credit card expiration date Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. # Date value. Includes year, month, day. See also: https://github.com/googleapis/googleapis/blob/master/google/type/date.proto
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"datetimeValue": { # Represents civil time (or occasionally physical time). This type can represent a civil time in one of a few possible ways: * When utc_offset is set and time_zone is unset: a civil time on a calendar day with a particular offset from UTC. * When time_zone is set and utc_offset is unset: a civil time on a calendar day in a particular time zone. * When neither time_zone nor utc_offset is set: a civil time on a calendar day in local time. The date is relative to the Proleptic Gregorian Calendar. If year is 0, the DateTime is considered not to have a specific year. month and day must have valid, non-zero values. This type may also be used to represent a physical time if all the date and time fields are set and either case of the `time_offset` oneof is set. Consider using `Timestamp` message for physical time instead. If your use case also would like to store the user's timezone, that can be done in another field. This type is more flexible than some applications may want. Make sure to document and validate your application's limitations. # DateTime value. Includes date, time, and timezone. See also: https://github.com/googleapis/googleapis/blob/master/google/type/datetime.proto
"day": 42, # Required. Day of month. Must be from 1 to 31 and valid for the year and month.
"hours": 42, # Required. Hours of day in 24 hour format. Should be from 0 to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Required. Minutes of hour of day. Must be from 0 to 59.
"month": 42, # Required. Month of year. Must be from 1 to 12.
"nanos": 42, # Required. Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Required. Seconds of minutes of the time. Must normally be from 0 to 59. An API may allow the value 60 if it allows leap-seconds.
"timeZone": { # Represents a time zone from the [IANA Time Zone Database](https://www.iana.org/time-zones). # Time zone.
"id": "A String", # IANA Time Zone Database time zone, e.g. "America/New_York".
"version": "A String", # Optional. IANA Time Zone Database version number, e.g. "2019a".
},
"utcOffset": "A String", # UTC offset. Must be whole seconds, between -18 hours and +18 hours. For example, a UTC offset of -4:00 would be represented as { seconds: -14400 }.
"year": 42, # Optional. Year of date. Must be from 1 to 9999, or 0 if specifying a datetime without a year.
},
"floatValue": 3.14, # Float value.
"integerValue": 42, # Integer value.
"moneyValue": { # Represents an amount of money with its currency type. # Money value. See also: https://github.com/googleapis/googleapis/blob/master/google/type/money.proto
"currencyCode": "A String", # The three-letter currency code defined in ISO 4217.
"nanos": 42, # Number of nano (10^-9) units of the amount. The value must be between -999,999,999 and +999,999,999 inclusive. If `units` is positive, `nanos` must be positive or zero. If `units` is zero, `nanos` can be positive, zero, or negative. If `units` is negative, `nanos` must be negative or zero. For example $-1.75 is represented as `units`=-1 and `nanos`=-750,000,000.
"units": "A String", # The whole units of the amount. For example if `currencyCode` is `"USD"`, then 1 unit is one US dollar.
},
"text": "A String", # Optional. An optional field to store a normalized string. For some entity types, one of respective 'structured_value' fields may also be populated. Also not all the types of 'structured_value' will be normalized. For example, some processors may not generate float or int normalized text by default. Below are sample formats mapped to structured values. - Money/Currency type (`money_value`) is in the ISO 4217 text format. - Date type (`date_value`) is in the ISO 8601 text format. - Datetime type (`datetime_value`) is in the ISO 8601 text format.
},
"pageAnchor": { # Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types. # Optional. Represents the provenance of this entity wrt. the location on the page where it was found.
"pageRefs": [ # One or more references to visual page elements
{ # Represents a weak reference to a page element within a document.
"boundingPoly": { # A bounding polygon for the detected image annotation. # Optional. Identifies the bounding polygon of a layout element on the page.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Optional. Confidence of detected page element, if applicable. Range [0, 1].
"layoutId": "A String", # Optional. Deprecated. Use PageRef.bounding_poly instead.
"layoutType": "A String", # Optional. The type of the layout element that is being referenced if any.
"page": "A String", # Required. Index into the Document.pages element, for example using Document.pages to locate the related page element. This field is skipped when its value is the default 0. See https://developers.google.com/protocol-buffers/docs/proto3#json.
},
],
},
"properties": [ # Optional. Entities can be nested to form a hierarchical data structure representing the content in the document.
# Object with schema name: GoogleCloudDocumentaiV1beta3DocumentEntity
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # Optional. The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"redacted": True or False, # Optional. Whether the entity will be redacted for de-identification purposes.
"textAnchor": { # Text reference indexing into the Document.text. # Optional. Provenance of the entity. Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
"type": "A String", # Entity type from a schema e.g. `Address`.
},
],
"entityRelations": [ # Relationship among Document.entities.
{ # Relationship between Entities.
"objectId": "A String", # Object entity id.
"relation": "A String", # Relationship description.
"subjectId": "A String", # Subject entity id.
},
],
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Any error that occurred while processing this document.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"mimeType": "A String", # An IANA published MIME type (also referred to as media type). For more information, see https://www.iana.org/assignments/media-types/media-types.xhtml.
"pages": [ # Visual page layout for the Document.
{ # A page in a Document.
"blocks": [ # A list of visually detected text blocks on the page. A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
{ # A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Block.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"dimension": { # Dimension for the page. # Physical dimension of the page.
"height": 3.14, # Page height.
"unit": "A String", # Dimension unit.
"width": 3.14, # Page width.
},
"formFields": [ # A list of visually detected form fields on the page.
{ # A form field detected on the page.
"correctedKeyText": "A String", # Created for Labeling UI to export key text. If corrections were made to the text identified by the `field_name.text_anchor`, this field will contain the correction.
"correctedValueText": "A String", # Created for Labeling UI to export value text. If corrections were made to the text identified by the `field_value.text_anchor`, this field will contain the correction.
"fieldName": { # Visual element describing a layout unit on a page. # Layout for the FormField name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"fieldValue": { # Visual element describing a layout unit on a page. # Layout for the FormField value.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"nameDetectedLanguages": [ # A list of detected languages for name together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"valueDetectedLanguages": [ # A list of detected languages for value together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"valueType": "A String", # If the value is non-textual, this field represents the type. Current valid values are: - blank (this indicates the field_value is normal text) - "unfilled_checkbox" - "filled_checkbox"
},
],
"image": { # Rendered image contents for this page. # Rendered image for this page. This image is preprocessed to remove any skew, rotation, and distortions such that the annotation bounding boxes can be upright and axis-aligned.
"content": "A String", # Raw byte content of the image.
"height": 42, # Height of the image in pixels.
"mimeType": "A String", # Encoding mime type for the image.
"width": 42, # Width of the image in pixels.
},
"layout": { # Visual element describing a layout unit on a page. # Layout for the page.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"lines": [ # A list of visually detected text lines on the page. A collection of tokens that a human would perceive as a line.
{ # A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Line.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"pageNumber": 42, # 1-based index for current Page in a parent Document. Useful when a page is taken out of a Document for individual processing.
"paragraphs": [ # A list of visually detected text paragraphs on the page. A collection of lines that a human would perceive as a paragraph.
{ # A collection of lines that a human would perceive as a paragraph.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Paragraph.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this page.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"tables": [ # A list of visually detected tables on the page.
{ # A table representation similar to HTML table structure.
"bodyRows": [ # Body rows of the table.
{ # A row of table cells.
"cells": [ # Cells that make up this row.
{ # A cell representation inside the table.
"colSpan": 42, # How many columns this cell spans.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"rowSpan": 42, # How many rows this cell spans.
},
],
},
],
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"headerRows": [ # Header rows of the table.
{ # A row of table cells.
"cells": [ # Cells that make up this row.
{ # A cell representation inside the table.
"colSpan": 42, # How many columns this cell spans.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"rowSpan": 42, # How many rows this cell spans.
},
],
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Table.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
},
],
"tokens": [ # A list of visually detected tokens on the page.
{ # A detected token.
"detectedBreak": { # Detected break at the end of a Token. # Detected break at the end of a Token.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Token.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"transforms": [ # Transformation matrices that were applied to the original document image to produce Page.image.
{ # Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.
"cols": 42, # Number of columns in the matrix.
"data": "A String", # The matrix data.
"rows": 42, # Number of rows in the matrix.
"type": 42, # This encodes information about what data type the matrix uses. For example, 0 (CV_8U) is an unsigned 8-bit image. For the full list of OpenCV primitive data types, please refer to https://docs.opencv.org/4.3.0/d1/d1b/group__core__hal__interface.html
},
],
"visualElements": [ # A list of detected non-text visual elements e.g. checkbox, signature etc. on the page.
{ # Detected non-text visual elements e.g. checkbox, signature etc. on the page.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for VisualElement.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"type": "A String", # Type of the VisualElement.
},
],
},
],
"revisions": [ # Revision history of this document.
{ # Contains past or forward revisions of this document.
"agent": "A String", # If the change was made by a person specify the name or id of that person.
"createTime": "A String", # The time that the revision was created.
"humanReview": { # Human Review information of the document. # Human Review information of this revision.
"state": "A String", # Human review state. e.g. `requested`, `succeeded`, `rejected`.
"stateMessage": "A String", # A message providing more details about the current state of processing. For example, the rejection reason when the state is `rejected`.
},
"id": "A String", # Id of the revision. Unique within the context of the document.
"parent": [ # The revisions that this revision is based on. This can include one or more parent (when documents are merged.) This field represents the index into the `revisions` field.
42,
],
"parentIds": [ # The revisions that this revision is based on. Must include all the ids that have anything to do with this revision - eg. there are `provenance.parent.revision` fields that index into this field.
"A String",
],
"processor": "A String", # If the annotation was made by processor identify the processor by its resource name.
},
],
"shardInfo": { # For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is. # Information about the sharding if this document is sharded part of a larger document. If the document is not sharded, this message is not specified.
"shardCount": "A String", # Total number of shards.
"shardIndex": "A String", # The 0-based index of this shard.
"textOffset": "A String", # The index of the first character in Document.text in the overall document global text.
},
"text": "A String", # Optional. UTF-8 encoded text in reading order from the document.
"textChanges": [ # A list of text corrections made to [Document.text]. This is usually used for annotating corrections to OCR mistakes. Text changes for a given revision may not overlap with each other.
{ # This message is used for text changes aka. OCR corrections.
"changedText": "A String", # The text that replaces the text identified in the `text_anchor`.
"provenance": [ # The history of this annotation.
{ # Structure to identify provenance relationships between annotations in different revisions.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
],
"textAnchor": { # Text reference indexing into the Document.text. # Provenance of the correction. Text anchor indexing into the Document.text. There can only be a single `TextAnchor.text_segments` element. If the start and end index of the text segment are the same, the text change is inserted before that index.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
],
"textStyles": [ # Styles for the Document.text.
{ # Annotation for common text style attributes. This adheres to CSS conventions as much as possible.
"backgroundColor": { # Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to/from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of `java.awt.Color` in Java; it can also be trivially provided to UIColor's `+colorWithRed:green:blue:alpha` method in iOS; and, with just a little work, it can be easily formatted into a CSS `rgba()` string in JavaScript. This reference page doesn't carry information about the absolute color space that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, DCI-P3, BT.2020, etc.). By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ... # Text background color.
"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, the final pixel color is defined by the equation: `pixel color = alpha * (this color) + (1.0 - alpha) * (background color)` This means that a value of 1.0 corresponds to a solid color, whereas a value of 0.0 corresponds to a completely transparent color. This uses a wrapper message rather than a simple float scalar so that it is possible to distinguish between a default value and the value being unset. If omitted, this color object is rendered as a solid color (as if the alpha value had been explicitly given a value of 1.0).
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"color": { # Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to/from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of `java.awt.Color` in Java; it can also be trivially provided to UIColor's `+colorWithRed:green:blue:alpha` method in iOS; and, with just a little work, it can be easily formatted into a CSS `rgba()` string in JavaScript. This reference page doesn't carry information about the absolute color space that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, DCI-P3, BT.2020, etc.). By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ... # Text color.
"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, the final pixel color is defined by the equation: `pixel color = alpha * (this color) + (1.0 - alpha) * (background color)` This means that a value of 1.0 corresponds to a solid color, whereas a value of 0.0 corresponds to a completely transparent color. This uses a wrapper message rather than a simple float scalar so that it is possible to distinguish between a default value and the value being unset. If omitted, this color object is rendered as a solid color (as if the alpha value had been explicitly given a value of 1.0).
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"fontSize": { # Font size with unit. # Font size.
"size": 3.14, # Font size for the text.
"unit": "A String", # Unit for the font size. Follows CSS naming (in, px, pt, etc.).
},
"fontWeight": "A String", # Font weight. Possible values are normal, bold, bolder, and lighter. https://www.w3schools.com/cssref/pr_font_weight.asp
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
"textDecoration": "A String", # Text decoration. Follows CSS standard. https://www.w3schools.com/cssref/pr_text_text-decoration.asp
"textStyle": "A String", # Text style. Possible values are normal, italic, and oblique. https://www.w3schools.com/cssref/pr_font_font-style.asp
},
],
"uri": "A String", # Optional. Currently supports Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. See [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris) for more info.
},
"inlineDocument": { # Document represents the canonical document resource in Document Understanding AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document Understanding AI to iterate and optimize for quality. # An inline document proto.
"content": "A String", # Optional. Inline document content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.
"entities": [ # A list of entities detected on Document.text. For document shards, entities in this list may cross shard boundaries.
{ # An entity that could be a phrase in the text or a property belongs to the document. It is a known entity type, such as a person, an organization, or location.
"confidence": 3.14, # Optional. Confidence of detected Schema entity. Range [0, 1].
"id": "A String", # Optional. Canonical id. This will be a unique value in the entity list for this document.
"mentionId": "A String", # Optional. Deprecated. Use `id` field instead.
"mentionText": "A String", # Optional. Text value in the document e.g. `1600 Amphitheatre Pkwy`. If the entity is not present in the document, this field will be empty.
"normalizedValue": { # Parsed and normalized entity value. # Optional. Normalized entity value. Absent if the extracted value could not be converted or the type (e.g. address) is not supported for certain parsers. This field is also only populated for certain supported document types.
"addressValue": { # Represents a postal address, e.g. for postal delivery or payments addresses. Given a postal address, a postal service can deliver items to a premise, P.O. Box or similar. It is not intended to model geographical locations (roads, towns, mountains). In typical usage an address would be created via user input or from importing existing data, depending on the type of process. Advice on address input / editing: - Use an i18n-ready address widget such as https://github.com/google/libaddressinput) - Users should not be presented with UI elements for input or editing of fields outside countries where that field is used. For more guidance on how to use this schema, please see: https://support.google.com/business/answer/6397478 # Postal address. See also: https://github.com/googleapis/googleapis/blob/master/google/type/postal_address.proto
"addressLines": [ # Unstructured address lines describing the lower levels of an address. Because values in address_lines do not have type information and may sometimes contain multiple values in a single field (e.g. "Austin, TX"), it is important that the line order is clear. The order of address lines should be "envelope order" for the country/region of the address. In places where this can vary (e.g. Japan), address_language is used to make it explicit (e.g. "ja" for large-to-small ordering and "ja-Latn" or "en" for small-to-large). This way, the most specific line of an address can be selected based on the language. The minimum permitted structural representation of an address consists of a region_code with all remaining information placed in the address_lines. It would be possible to format such an address very approximately without geocoding, but no semantic reasoning could be made about any of the address components until it was at least partially resolved. Creating an address only containing a region_code and address_lines, and then geocoding is the recommended way to handle completely unstructured addresses (as opposed to guessing which parts of the address should be localities or administrative areas).
"A String",
],
"administrativeArea": "A String", # Optional. Highest administrative subdivision which is used for postal addresses of a country or region. For example, this can be a state, a province, an oblast, or a prefecture. Specifically, for Spain this is the province and not the autonomous community (e.g. "Barcelona" and not "Catalonia"). Many countries don't use an administrative area in postal addresses. E.g. in Switzerland this should be left unpopulated.
"languageCode": "A String", # Optional. BCP-47 language code of the contents of this address (if known). This is often the UI language of the input form or is expected to match one of the languages used in the address' country/region, or their transliterated equivalents. This can affect formatting in certain countries, but is not critical to the correctness of the data and will never affect any validation or other non-formatting related operations. If this value is not known, it should be omitted (rather than specifying a possibly incorrect default). Examples: "zh-Hant", "ja", "ja-Latn", "en".
"locality": "A String", # Optional. Generally refers to the city/town portion of the address. Examples: US city, IT comune, UK post town. In regions of the world where localities are not well defined or do not fit into this structure well, leave locality empty and use address_lines.
"organization": "A String", # Optional. The name of the organization at the address.
"postalCode": "A String", # Optional. Postal code of the address. Not all countries use or require postal codes to be present, but where they are used, they may trigger additional validation with other parts of the address (e.g. state/zip validation in the U.S.A.).
"recipients": [ # Optional. The recipient at the address. This field may, under certain circumstances, contain multiline information. For example, it might contain "care of" information.
"A String",
],
"regionCode": "A String", # Required. CLDR region code of the country/region of the address. This is never inferred and it is up to the user to ensure the value is correct. See http://cldr.unicode.org/ and http://www.unicode.org/cldr/charts/30/supplemental/territory_information.html for details. Example: "CH" for Switzerland.
"revision": 42, # The schema revision of the `PostalAddress`. This must be set to 0, which is the latest revision. All new revisions **must** be backward compatible with old revisions.
"sortingCode": "A String", # Optional. Additional, country-specific, sorting code. This is not used in most regions. Where it is used, the value is either a string like "CEDEX", optionally followed by a number (e.g. "CEDEX 7"), or just a number alone, representing the "sector code" (Jamaica), "delivery area indicator" (Malawi) or "post office indicator" (e.g. Côte d'Ivoire).
"sublocality": "A String", # Optional. Sublocality of the address. For example, this can be neighborhoods, boroughs, districts.
},
"booleanValue": True or False, # Boolean value. Can be used for entities with binary values, or for checkboxes.
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values * A month and day value, with a zero year, such as an anniversary * A year on its own, with zero month and day values * A year and month value, with a zero day, such as a credit card expiration date Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. # Date value. Includes year, month, day. See also: https://github.com/googleapis/googleapis/blob/master/google/type/date.proto
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"datetimeValue": { # Represents civil time (or occasionally physical time). This type can represent a civil time in one of a few possible ways: * When utc_offset is set and time_zone is unset: a civil time on a calendar day with a particular offset from UTC. * When time_zone is set and utc_offset is unset: a civil time on a calendar day in a particular time zone. * When neither time_zone nor utc_offset is set: a civil time on a calendar day in local time. The date is relative to the Proleptic Gregorian Calendar. If year is 0, the DateTime is considered not to have a specific year. month and day must have valid, non-zero values. This type may also be used to represent a physical time if all the date and time fields are set and either case of the `time_offset` oneof is set. Consider using `Timestamp` message for physical time instead. If your use case also would like to store the user's timezone, that can be done in another field. This type is more flexible than some applications may want. Make sure to document and validate your application's limitations. # DateTime value. Includes date, time, and timezone. See also: https://github.com/googleapis/googleapis/blob/master/google/type/datetime.proto
"day": 42, # Required. Day of month. Must be from 1 to 31 and valid for the year and month.
"hours": 42, # Required. Hours of day in 24 hour format. Should be from 0 to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Required. Minutes of hour of day. Must be from 0 to 59.
"month": 42, # Required. Month of year. Must be from 1 to 12.
"nanos": 42, # Required. Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Required. Seconds of minutes of the time. Must normally be from 0 to 59. An API may allow the value 60 if it allows leap-seconds.
"timeZone": { # Represents a time zone from the [IANA Time Zone Database](https://www.iana.org/time-zones). # Time zone.
"id": "A String", # IANA Time Zone Database time zone, e.g. "America/New_York".
"version": "A String", # Optional. IANA Time Zone Database version number, e.g. "2019a".
},
"utcOffset": "A String", # UTC offset. Must be whole seconds, between -18 hours and +18 hours. For example, a UTC offset of -4:00 would be represented as { seconds: -14400 }.
"year": 42, # Optional. Year of date. Must be from 1 to 9999, or 0 if specifying a datetime without a year.
},
"floatValue": 3.14, # Float value.
"integerValue": 42, # Integer value.
"moneyValue": { # Represents an amount of money with its currency type. # Money value. See also: https://github.com/googleapis/googleapis/blob/master/google/type/money.proto
"currencyCode": "A String", # The three-letter currency code defined in ISO 4217.
"nanos": 42, # Number of nano (10^-9) units of the amount. The value must be between -999,999,999 and +999,999,999 inclusive. If `units` is positive, `nanos` must be positive or zero. If `units` is zero, `nanos` can be positive, zero, or negative. If `units` is negative, `nanos` must be negative or zero. For example $-1.75 is represented as `units`=-1 and `nanos`=-750,000,000.
"units": "A String", # The whole units of the amount. For example if `currencyCode` is `"USD"`, then 1 unit is one US dollar.
},
"text": "A String", # Optional. An optional field to store a normalized string. For some entity types, one of respective 'structured_value' fields may also be populated. Also not all the types of 'structured_value' will be normalized. For example, some processors may not generate float or int normalized text by default. Below are sample formats mapped to structured values. - Money/Currency type (`money_value`) is in the ISO 4217 text format. - Date type (`date_value`) is in the ISO 8601 text format. - Datetime type (`datetime_value`) is in the ISO 8601 text format.
},
"pageAnchor": { # Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types. # Optional. Represents the provenance of this entity wrt. the location on the page where it was found.
"pageRefs": [ # One or more references to visual page elements
{ # Represents a weak reference to a page element within a document.
"boundingPoly": { # A bounding polygon for the detected image annotation. # Optional. Identifies the bounding polygon of a layout element on the page.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Optional. Confidence of detected page element, if applicable. Range [0, 1].
"layoutId": "A String", # Optional. Deprecated. Use PageRef.bounding_poly instead.
"layoutType": "A String", # Optional. The type of the layout element that is being referenced if any.
"page": "A String", # Required. Index into the Document.pages element, for example using Document.pages to locate the related page element. This field is skipped when its value is the default 0. See https://developers.google.com/protocol-buffers/docs/proto3#json.
},
],
},
"properties": [ # Optional. Entities can be nested to form a hierarchical data structure representing the content in the document.
# Object with schema name: GoogleCloudDocumentaiV1beta3DocumentEntity
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # Optional. The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"redacted": True or False, # Optional. Whether the entity will be redacted for de-identification purposes.
"textAnchor": { # Text reference indexing into the Document.text. # Optional. Provenance of the entity. Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
"type": "A String", # Entity type from a schema e.g. `Address`.
},
],
"entityRelations": [ # Relationship among Document.entities.
{ # Relationship between Entities.
"objectId": "A String", # Object entity id.
"relation": "A String", # Relationship description.
"subjectId": "A String", # Subject entity id.
},
],
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Any error that occurred while processing this document.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"mimeType": "A String", # An IANA published MIME type (also referred to as media type). For more information, see https://www.iana.org/assignments/media-types/media-types.xhtml.
"pages": [ # Visual page layout for the Document.
{ # A page in a Document.
"blocks": [ # A list of visually detected text blocks on the page. A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
{ # A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Block.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"dimension": { # Dimension for the page. # Physical dimension of the page.
"height": 3.14, # Page height.
"unit": "A String", # Dimension unit.
"width": 3.14, # Page width.
},
"formFields": [ # A list of visually detected form fields on the page.
{ # A form field detected on the page.
"correctedKeyText": "A String", # Created for Labeling UI to export key text. If corrections were made to the text identified by the `field_name.text_anchor`, this field will contain the correction.
"correctedValueText": "A String", # Created for Labeling UI to export value text. If corrections were made to the text identified by the `field_value.text_anchor`, this field will contain the correction.
"fieldName": { # Visual element describing a layout unit on a page. # Layout for the FormField name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"fieldValue": { # Visual element describing a layout unit on a page. # Layout for the FormField value.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"nameDetectedLanguages": [ # A list of detected languages for name together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"valueDetectedLanguages": [ # A list of detected languages for value together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"valueType": "A String", # If the value is non-textual, this field represents the type. Current valid values are: - blank (this indicates the field_value is normal text) - "unfilled_checkbox" - "filled_checkbox"
},
],
"image": { # Rendered image contents for this page. # Rendered image for this page. This image is preprocessed to remove any skew, rotation, and distortions such that the annotation bounding boxes can be upright and axis-aligned.
"content": "A String", # Raw byte content of the image.
"height": 42, # Height of the image in pixels.
"mimeType": "A String", # Encoding mime type for the image.
"width": 42, # Width of the image in pixels.
},
"layout": { # Visual element describing a layout unit on a page. # Layout for the page.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"lines": [ # A list of visually detected text lines on the page. A collection of tokens that a human would perceive as a line.
{ # A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Line.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"pageNumber": 42, # 1-based index for current Page in a parent Document. Useful when a page is taken out of a Document for individual processing.
"paragraphs": [ # A list of visually detected text paragraphs on the page. A collection of lines that a human would perceive as a paragraph.
{ # A collection of lines that a human would perceive as a paragraph.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Paragraph.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this page.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"tables": [ # A list of visually detected tables on the page.
{ # A table representation similar to HTML table structure.
"bodyRows": [ # Body rows of the table.
{ # A row of table cells.
"cells": [ # Cells that make up this row.
{ # A cell representation inside the table.
"colSpan": 42, # How many columns this cell spans.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"rowSpan": 42, # How many rows this cell spans.
},
],
},
],
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"headerRows": [ # Header rows of the table.
{ # A row of table cells.
"cells": [ # Cells that make up this row.
{ # A cell representation inside the table.
"colSpan": 42, # How many columns this cell spans.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"rowSpan": 42, # How many rows this cell spans.
},
],
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Table.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
},
],
"tokens": [ # A list of visually detected tokens on the page.
{ # A detected token.
"detectedBreak": { # Detected break at the end of a Token. # Detected break at the end of a Token.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Token.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"transforms": [ # Transformation matrices that were applied to the original document image to produce Page.image.
{ # Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.
"cols": 42, # Number of columns in the matrix.
"data": "A String", # The matrix data.
"rows": 42, # Number of rows in the matrix.
"type": 42, # This encodes information about what data type the matrix uses. For example, 0 (CV_8U) is an unsigned 8-bit image. For the full list of OpenCV primitive data types, please refer to https://docs.opencv.org/4.3.0/d1/d1b/group__core__hal__interface.html
},
],
"visualElements": [ # A list of detected non-text visual elements e.g. checkbox, signature etc. on the page.
{ # Detected non-text visual elements e.g. checkbox, signature etc. on the page.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for VisualElement.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"type": "A String", # Type of the VisualElement.
},
],
},
],
"revisions": [ # Revision history of this document.
{ # Contains past or forward revisions of this document.
"agent": "A String", # If the change was made by a person specify the name or id of that person.
"createTime": "A String", # The time that the revision was created.
"humanReview": { # Human Review information of the document. # Human Review information of this revision.
"state": "A String", # Human review state. e.g. `requested`, `succeeded`, `rejected`.
"stateMessage": "A String", # A message providing more details about the current state of processing. For example, the rejection reason when the state is `rejected`.
},
"id": "A String", # Id of the revision. Unique within the context of the document.
"parent": [ # The revisions that this revision is based on. This can include one or more parent (when documents are merged.) This field represents the index into the `revisions` field.
42,
],
"parentIds": [ # The revisions that this revision is based on. Must include all the ids that have anything to do with this revision - eg. there are `provenance.parent.revision` fields that index into this field.
"A String",
],
"processor": "A String", # If the annotation was made by processor identify the processor by its resource name.
},
],
"shardInfo": { # For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is. # Information about the sharding if this document is sharded part of a larger document. If the document is not sharded, this message is not specified.
"shardCount": "A String", # Total number of shards.
"shardIndex": "A String", # The 0-based index of this shard.
"textOffset": "A String", # The index of the first character in Document.text in the overall document global text.
},
"text": "A String", # Optional. UTF-8 encoded text in reading order from the document.
"textChanges": [ # A list of text corrections made to [Document.text]. This is usually used for annotating corrections to OCR mistakes. Text changes for a given revision may not overlap with each other.
{ # This message is used for text changes aka. OCR corrections.
"changedText": "A String", # The text that replaces the text identified in the `text_anchor`.
"provenance": [ # The history of this annotation.
{ # Structure to identify provenance relationships between annotations in different revisions.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
],
"textAnchor": { # Text reference indexing into the Document.text. # Provenance of the correction. Text anchor indexing into the Document.text. There can only be a single `TextAnchor.text_segments` element. If the start and end index of the text segment are the same, the text change is inserted before that index.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
],
"textStyles": [ # Styles for the Document.text.
{ # Annotation for common text style attributes. This adheres to CSS conventions as much as possible.
"backgroundColor": { # Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to/from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of `java.awt.Color` in Java; it can also be trivially provided to UIColor's `+colorWithRed:green:blue:alpha` method in iOS; and, with just a little work, it can be easily formatted into a CSS `rgba()` string in JavaScript. This reference page doesn't carry information about the absolute color space that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, DCI-P3, BT.2020, etc.). By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ... # Text background color.
"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, the final pixel color is defined by the equation: `pixel color = alpha * (this color) + (1.0 - alpha) * (background color)` This means that a value of 1.0 corresponds to a solid color, whereas a value of 0.0 corresponds to a completely transparent color. This uses a wrapper message rather than a simple float scalar so that it is possible to distinguish between a default value and the value being unset. If omitted, this color object is rendered as a solid color (as if the alpha value had been explicitly given a value of 1.0).
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"color": { # Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to/from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of `java.awt.Color` in Java; it can also be trivially provided to UIColor's `+colorWithRed:green:blue:alpha` method in iOS; and, with just a little work, it can be easily formatted into a CSS `rgba()` string in JavaScript. This reference page doesn't carry information about the absolute color space that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, DCI-P3, BT.2020, etc.). By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ... # Text color.
"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, the final pixel color is defined by the equation: `pixel color = alpha * (this color) + (1.0 - alpha) * (background color)` This means that a value of 1.0 corresponds to a solid color, whereas a value of 0.0 corresponds to a completely transparent color. This uses a wrapper message rather than a simple float scalar so that it is possible to distinguish between a default value and the value being unset. If omitted, this color object is rendered as a solid color (as if the alpha value had been explicitly given a value of 1.0).
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"fontSize": { # Font size with unit. # Font size.
"size": 3.14, # Font size for the text.
"unit": "A String", # Unit for the font size. Follows CSS naming (in, px, pt, etc.).
},
"fontWeight": "A String", # Font weight. Possible values are normal, bold, bolder, and lighter. https://www.w3schools.com/cssref/pr_font_weight.asp
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
"textDecoration": "A String", # Text decoration. Follows CSS standard. https://www.w3schools.com/cssref/pr_text_text-decoration.asp
"textStyle": "A String", # Text style. Possible values are normal, italic, and oblique. https://www.w3schools.com/cssref/pr_font_font-style.asp
},
],
"uri": "A String", # Optional. Currently supports Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. See [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris) for more info.
},
"rawDocument": { # Payload message of raw document content (bytes). # A raw document content (bytes).
"content": "A String", # Inline document content.
"mimeType": "A String", # An IANA MIME type (RFC6838) indicating the nature and format of the [content].
},
"skipHumanReview": True or False, # Whether Human Review feature should be skipped for this request. Default to false.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for the process document method.
"document": { # Document represents the canonical document resource in Document Understanding AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document Understanding AI to iterate and optimize for quality. # The document payload, will populate fields based on the processor's behavior.
"content": "A String", # Optional. Inline document content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.
"entities": [ # A list of entities detected on Document.text. For document shards, entities in this list may cross shard boundaries.
{ # An entity that could be a phrase in the text or a property belongs to the document. It is a known entity type, such as a person, an organization, or location.
"confidence": 3.14, # Optional. Confidence of detected Schema entity. Range [0, 1].
"id": "A String", # Optional. Canonical id. This will be a unique value in the entity list for this document.
"mentionId": "A String", # Optional. Deprecated. Use `id` field instead.
"mentionText": "A String", # Optional. Text value in the document e.g. `1600 Amphitheatre Pkwy`. If the entity is not present in the document, this field will be empty.
"normalizedValue": { # Parsed and normalized entity value. # Optional. Normalized entity value. Absent if the extracted value could not be converted or the type (e.g. address) is not supported for certain parsers. This field is also only populated for certain supported document types.
"addressValue": { # Represents a postal address, e.g. for postal delivery or payments addresses. Given a postal address, a postal service can deliver items to a premise, P.O. Box or similar. It is not intended to model geographical locations (roads, towns, mountains). In typical usage an address would be created via user input or from importing existing data, depending on the type of process. Advice on address input / editing: - Use an i18n-ready address widget such as https://github.com/google/libaddressinput) - Users should not be presented with UI elements for input or editing of fields outside countries where that field is used. For more guidance on how to use this schema, please see: https://support.google.com/business/answer/6397478 # Postal address. See also: https://github.com/googleapis/googleapis/blob/master/google/type/postal_address.proto
"addressLines": [ # Unstructured address lines describing the lower levels of an address. Because values in address_lines do not have type information and may sometimes contain multiple values in a single field (e.g. "Austin, TX"), it is important that the line order is clear. The order of address lines should be "envelope order" for the country/region of the address. In places where this can vary (e.g. Japan), address_language is used to make it explicit (e.g. "ja" for large-to-small ordering and "ja-Latn" or "en" for small-to-large). This way, the most specific line of an address can be selected based on the language. The minimum permitted structural representation of an address consists of a region_code with all remaining information placed in the address_lines. It would be possible to format such an address very approximately without geocoding, but no semantic reasoning could be made about any of the address components until it was at least partially resolved. Creating an address only containing a region_code and address_lines, and then geocoding is the recommended way to handle completely unstructured addresses (as opposed to guessing which parts of the address should be localities or administrative areas).
"A String",
],
"administrativeArea": "A String", # Optional. Highest administrative subdivision which is used for postal addresses of a country or region. For example, this can be a state, a province, an oblast, or a prefecture. Specifically, for Spain this is the province and not the autonomous community (e.g. "Barcelona" and not "Catalonia"). Many countries don't use an administrative area in postal addresses. E.g. in Switzerland this should be left unpopulated.
"languageCode": "A String", # Optional. BCP-47 language code of the contents of this address (if known). This is often the UI language of the input form or is expected to match one of the languages used in the address' country/region, or their transliterated equivalents. This can affect formatting in certain countries, but is not critical to the correctness of the data and will never affect any validation or other non-formatting related operations. If this value is not known, it should be omitted (rather than specifying a possibly incorrect default). Examples: "zh-Hant", "ja", "ja-Latn", "en".
"locality": "A String", # Optional. Generally refers to the city/town portion of the address. Examples: US city, IT comune, UK post town. In regions of the world where localities are not well defined or do not fit into this structure well, leave locality empty and use address_lines.
"organization": "A String", # Optional. The name of the organization at the address.
"postalCode": "A String", # Optional. Postal code of the address. Not all countries use or require postal codes to be present, but where they are used, they may trigger additional validation with other parts of the address (e.g. state/zip validation in the U.S.A.).
"recipients": [ # Optional. The recipient at the address. This field may, under certain circumstances, contain multiline information. For example, it might contain "care of" information.
"A String",
],
"regionCode": "A String", # Required. CLDR region code of the country/region of the address. This is never inferred and it is up to the user to ensure the value is correct. See http://cldr.unicode.org/ and http://www.unicode.org/cldr/charts/30/supplemental/territory_information.html for details. Example: "CH" for Switzerland.
"revision": 42, # The schema revision of the `PostalAddress`. This must be set to 0, which is the latest revision. All new revisions **must** be backward compatible with old revisions.
"sortingCode": "A String", # Optional. Additional, country-specific, sorting code. This is not used in most regions. Where it is used, the value is either a string like "CEDEX", optionally followed by a number (e.g. "CEDEX 7"), or just a number alone, representing the "sector code" (Jamaica), "delivery area indicator" (Malawi) or "post office indicator" (e.g. Côte d'Ivoire).
"sublocality": "A String", # Optional. Sublocality of the address. For example, this can be neighborhoods, boroughs, districts.
},
"booleanValue": True or False, # Boolean value. Can be used for entities with binary values, or for checkboxes.
"dateValue": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values * A month and day value, with a zero year, such as an anniversary * A year on its own, with zero month and day values * A year and month value, with a zero day, such as a credit card expiration date Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. # Date value. Includes year, month, day. See also: https://github.com/googleapis/googleapis/blob/master/google/type/date.proto
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"datetimeValue": { # Represents civil time (or occasionally physical time). This type can represent a civil time in one of a few possible ways: * When utc_offset is set and time_zone is unset: a civil time on a calendar day with a particular offset from UTC. * When time_zone is set and utc_offset is unset: a civil time on a calendar day in a particular time zone. * When neither time_zone nor utc_offset is set: a civil time on a calendar day in local time. The date is relative to the Proleptic Gregorian Calendar. If year is 0, the DateTime is considered not to have a specific year. month and day must have valid, non-zero values. This type may also be used to represent a physical time if all the date and time fields are set and either case of the `time_offset` oneof is set. Consider using `Timestamp` message for physical time instead. If your use case also would like to store the user's timezone, that can be done in another field. This type is more flexible than some applications may want. Make sure to document and validate your application's limitations. # DateTime value. Includes date, time, and timezone. See also: https://github.com/googleapis/googleapis/blob/master/google/type/datetime.proto
"day": 42, # Required. Day of month. Must be from 1 to 31 and valid for the year and month.
"hours": 42, # Required. Hours of day in 24 hour format. Should be from 0 to 23. An API may choose to allow the value "24:00:00" for scenarios like business closing time.
"minutes": 42, # Required. Minutes of hour of day. Must be from 0 to 59.
"month": 42, # Required. Month of year. Must be from 1 to 12.
"nanos": 42, # Required. Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
"seconds": 42, # Required. Seconds of minutes of the time. Must normally be from 0 to 59. An API may allow the value 60 if it allows leap-seconds.
"timeZone": { # Represents a time zone from the [IANA Time Zone Database](https://www.iana.org/time-zones). # Time zone.
"id": "A String", # IANA Time Zone Database time zone, e.g. "America/New_York".
"version": "A String", # Optional. IANA Time Zone Database version number, e.g. "2019a".
},
"utcOffset": "A String", # UTC offset. Must be whole seconds, between -18 hours and +18 hours. For example, a UTC offset of -4:00 would be represented as { seconds: -14400 }.
"year": 42, # Optional. Year of date. Must be from 1 to 9999, or 0 if specifying a datetime without a year.
},
"floatValue": 3.14, # Float value.
"integerValue": 42, # Integer value.
"moneyValue": { # Represents an amount of money with its currency type. # Money value. See also: https://github.com/googleapis/googleapis/blob/master/google/type/money.proto
"currencyCode": "A String", # The three-letter currency code defined in ISO 4217.
"nanos": 42, # Number of nano (10^-9) units of the amount. The value must be between -999,999,999 and +999,999,999 inclusive. If `units` is positive, `nanos` must be positive or zero. If `units` is zero, `nanos` can be positive, zero, or negative. If `units` is negative, `nanos` must be negative or zero. For example $-1.75 is represented as `units`=-1 and `nanos`=-750,000,000.
"units": "A String", # The whole units of the amount. For example if `currencyCode` is `"USD"`, then 1 unit is one US dollar.
},
"text": "A String", # Optional. An optional field to store a normalized string. For some entity types, one of respective 'structured_value' fields may also be populated. Also not all the types of 'structured_value' will be normalized. For example, some processors may not generate float or int normalized text by default. Below are sample formats mapped to structured values. - Money/Currency type (`money_value`) is in the ISO 4217 text format. - Date type (`date_value`) is in the ISO 8601 text format. - Datetime type (`datetime_value`) is in the ISO 8601 text format.
},
"pageAnchor": { # Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types. # Optional. Represents the provenance of this entity wrt. the location on the page where it was found.
"pageRefs": [ # One or more references to visual page elements
{ # Represents a weak reference to a page element within a document.
"boundingPoly": { # A bounding polygon for the detected image annotation. # Optional. Identifies the bounding polygon of a layout element on the page.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Optional. Confidence of detected page element, if applicable. Range [0, 1].
"layoutId": "A String", # Optional. Deprecated. Use PageRef.bounding_poly instead.
"layoutType": "A String", # Optional. The type of the layout element that is being referenced if any.
"page": "A String", # Required. Index into the Document.pages element, for example using Document.pages to locate the related page element. This field is skipped when its value is the default 0. See https://developers.google.com/protocol-buffers/docs/proto3#json.
},
],
},
"properties": [ # Optional. Entities can be nested to form a hierarchical data structure representing the content in the document.
# Object with schema name: GoogleCloudDocumentaiV1beta3DocumentEntity
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # Optional. The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"redacted": True or False, # Optional. Whether the entity will be redacted for de-identification purposes.
"textAnchor": { # Text reference indexing into the Document.text. # Optional. Provenance of the entity. Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
"type": "A String", # Entity type from a schema e.g. `Address`.
},
],
"entityRelations": [ # Relationship among Document.entities.
{ # Relationship between Entities.
"objectId": "A String", # Object entity id.
"relation": "A String", # Relationship description.
"subjectId": "A String", # Subject entity id.
},
],
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Any error that occurred while processing this document.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"mimeType": "A String", # An IANA published MIME type (also referred to as media type). For more information, see https://www.iana.org/assignments/media-types/media-types.xhtml.
"pages": [ # Visual page layout for the Document.
{ # A page in a Document.
"blocks": [ # A list of visually detected text blocks on the page. A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
{ # A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Block.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"dimension": { # Dimension for the page. # Physical dimension of the page.
"height": 3.14, # Page height.
"unit": "A String", # Dimension unit.
"width": 3.14, # Page width.
},
"formFields": [ # A list of visually detected form fields on the page.
{ # A form field detected on the page.
"correctedKeyText": "A String", # Created for Labeling UI to export key text. If corrections were made to the text identified by the `field_name.text_anchor`, this field will contain the correction.
"correctedValueText": "A String", # Created for Labeling UI to export value text. If corrections were made to the text identified by the `field_value.text_anchor`, this field will contain the correction.
"fieldName": { # Visual element describing a layout unit on a page. # Layout for the FormField name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"fieldValue": { # Visual element describing a layout unit on a page. # Layout for the FormField value.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"nameDetectedLanguages": [ # A list of detected languages for name together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"valueDetectedLanguages": [ # A list of detected languages for value together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"valueType": "A String", # If the value is non-textual, this field represents the type. Current valid values are: - blank (this indicates the field_value is normal text) - "unfilled_checkbox" - "filled_checkbox"
},
],
"image": { # Rendered image contents for this page. # Rendered image for this page. This image is preprocessed to remove any skew, rotation, and distortions such that the annotation bounding boxes can be upright and axis-aligned.
"content": "A String", # Raw byte content of the image.
"height": 42, # Height of the image in pixels.
"mimeType": "A String", # Encoding mime type for the image.
"width": 42, # Width of the image in pixels.
},
"layout": { # Visual element describing a layout unit on a page. # Layout for the page.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"lines": [ # A list of visually detected text lines on the page. A collection of tokens that a human would perceive as a line.
{ # A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Line.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"pageNumber": 42, # 1-based index for current Page in a parent Document. Useful when a page is taken out of a Document for individual processing.
"paragraphs": [ # A list of visually detected text paragraphs on the page. A collection of lines that a human would perceive as a paragraph.
{ # A collection of lines that a human would perceive as a paragraph.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Paragraph.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this page.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
"tables": [ # A list of visually detected tables on the page.
{ # A table representation similar to HTML table structure.
"bodyRows": [ # Body rows of the table.
{ # A row of table cells.
"cells": [ # Cells that make up this row.
{ # A cell representation inside the table.
"colSpan": 42, # How many columns this cell spans.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"rowSpan": 42, # How many rows this cell spans.
},
],
},
],
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"headerRows": [ # Header rows of the table.
{ # A row of table cells.
"cells": [ # Cells that make up this row.
{ # A cell representation inside the table.
"colSpan": 42, # How many columns this cell spans.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"rowSpan": 42, # How many rows this cell spans.
},
],
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Table.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
},
],
"tokens": [ # A list of visually detected tokens on the page.
{ # A detected token.
"detectedBreak": { # Detected break at the end of a Token. # Detected break at the end of a Token.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for Token.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"provenance": { # Structure to identify provenance relationships between annotations in different revisions. # The history of this annotation.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
},
],
"transforms": [ # Transformation matrices that were applied to the original document image to produce Page.image.
{ # Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.
"cols": 42, # Number of columns in the matrix.
"data": "A String", # The matrix data.
"rows": 42, # Number of rows in the matrix.
"type": 42, # This encodes information about what data type the matrix uses. For example, 0 (CV_8U) is an unsigned 8-bit image. For the full list of OpenCV primitive data types, please refer to https://docs.opencv.org/4.3.0/d1/d1b/group__core__hal__interface.html
},
],
"visualElements": [ # A list of detected non-text visual elements e.g. checkbox, signature etc. on the page.
{ # Detected non-text visual elements e.g. checkbox, signature etc. on the page.
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
},
],
"layout": { # Visual element describing a layout unit on a page. # Layout for VisualElement.
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.
"normalizedVertices": [ # The bounding polygon normalized vertices.
{ # A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
"x": 3.14, # X coordinate.
"y": 3.14, # Y coordinate (starts from the top of the image).
},
],
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
"x": 42, # X coordinate.
"y": 42, # Y coordinate (starts from the top of the image).
},
],
},
"confidence": 3.14, # Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range [0, 1].
"orientation": "A String", # Detected orientation for the Layout.
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
"type": "A String", # Type of the VisualElement.
},
],
},
],
"revisions": [ # Revision history of this document.
{ # Contains past or forward revisions of this document.
"agent": "A String", # If the change was made by a person specify the name or id of that person.
"createTime": "A String", # The time that the revision was created.
"humanReview": { # Human Review information of the document. # Human Review information of this revision.
"state": "A String", # Human review state. e.g. `requested`, `succeeded`, `rejected`.
"stateMessage": "A String", # A message providing more details about the current state of processing. For example, the rejection reason when the state is `rejected`.
},
"id": "A String", # Id of the revision. Unique within the context of the document.
"parent": [ # The revisions that this revision is based on. This can include one or more parent (when documents are merged.) This field represents the index into the `revisions` field.
42,
],
"parentIds": [ # The revisions that this revision is based on. Must include all the ids that have anything to do with this revision - eg. there are `provenance.parent.revision` fields that index into this field.
"A String",
],
"processor": "A String", # If the annotation was made by processor identify the processor by its resource name.
},
],
"shardInfo": { # For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is. # Information about the sharding if this document is sharded part of a larger document. If the document is not sharded, this message is not specified.
"shardCount": "A String", # Total number of shards.
"shardIndex": "A String", # The 0-based index of this shard.
"textOffset": "A String", # The index of the first character in Document.text in the overall document global text.
},
"text": "A String", # Optional. UTF-8 encoded text in reading order from the document.
"textChanges": [ # A list of text corrections made to [Document.text]. This is usually used for annotating corrections to OCR mistakes. Text changes for a given revision may not overlap with each other.
{ # This message is used for text changes aka. OCR corrections.
"changedText": "A String", # The text that replaces the text identified in the `text_anchor`.
"provenance": [ # The history of this annotation.
{ # Structure to identify provenance relationships between annotations in different revisions.
"id": 42, # The Id of this operation. Needs to be unique within the scope of the revision.
"parents": [ # References to the original elements that are replaced.
{ # The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.
"id": 42, # The id of the parent provenance.
"index": 42, # The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) on parent revision.
"revision": 42, # The index of the index into current revision's parent_ids list.
},
],
"revision": 42, # The index of the revision that produced this element.
"type": "A String", # The type of provenance operation.
},
],
"textAnchor": { # Text reference indexing into the Document.text. # Provenance of the correction. Text anchor indexing into the Document.text. There can only be a single `TextAnchor.text_segments` element. If the start and end index of the text segment are the same, the text change is inserted before that index.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
},
],
"textStyles": [ # Styles for the Document.text.
{ # Annotation for common text style attributes. This adheres to CSS conventions as much as possible.
"backgroundColor": { # Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to/from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of `java.awt.Color` in Java; it can also be trivially provided to UIColor's `+colorWithRed:green:blue:alpha` method in iOS; and, with just a little work, it can be easily formatted into a CSS `rgba()` string in JavaScript. This reference page doesn't carry information about the absolute color space that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, DCI-P3, BT.2020, etc.). By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ... # Text background color.
"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, the final pixel color is defined by the equation: `pixel color = alpha * (this color) + (1.0 - alpha) * (background color)` This means that a value of 1.0 corresponds to a solid color, whereas a value of 0.0 corresponds to a completely transparent color. This uses a wrapper message rather than a simple float scalar so that it is possible to distinguish between a default value and the value being unset. If omitted, this color object is rendered as a solid color (as if the alpha value had been explicitly given a value of 1.0).
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"color": { # Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to/from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of `java.awt.Color` in Java; it can also be trivially provided to UIColor's `+colorWithRed:green:blue:alpha` method in iOS; and, with just a little work, it can be easily formatted into a CSS `rgba()` string in JavaScript. This reference page doesn't carry information about the absolute color space that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, DCI-P3, BT.2020, etc.). By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ... # Text color.
"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, the final pixel color is defined by the equation: `pixel color = alpha * (this color) + (1.0 - alpha) * (background color)` This means that a value of 1.0 corresponds to a solid color, whereas a value of 0.0 corresponds to a completely transparent color. This uses a wrapper message rather than a simple float scalar so that it is possible to distinguish between a default value and the value being unset. If omitted, this color object is rendered as a solid color (as if the alpha value had been explicitly given a value of 1.0).
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"fontSize": { # Font size with unit. # Font size.
"size": 3.14, # Font size for the text.
"unit": "A String", # Unit for the font size. Follows CSS naming (in, px, pt, etc.).
},
"fontWeight": "A String", # Font weight. Possible values are normal, bold, bolder, and lighter. https://www.w3schools.com/cssref/pr_font_weight.asp
"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.
"content": "A String", # Contains the content of the text span so that users do not have to look it up in the text_segments.
"textSegments": [ # The text segments from the Document.text.
{ # A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset
"endIndex": "A String", # TextSegment half open end UTF-8 char index in the Document.text.
"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.
},
],
},
"textDecoration": "A String", # Text decoration. Follows CSS standard. https://www.w3schools.com/cssref/pr_text_text-decoration.asp
"textStyle": "A String", # Text style. Possible values are normal, italic, and oblique. https://www.w3schools.com/cssref/pr_font_font-style.asp
},
],
"uri": "A String", # Optional. Currently supports Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. See [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris) for more info.
},
"humanReviewOperation": "A String", # The name of the operation triggered by the processed document. If the human review process is not triggered, this field will be empty. It has the same response type and metadata as the long running operation returned by ReviewDocument method.
"humanReviewStatus": { # The status of human review on a processed document. # The status of human review on the processed document.
"humanReviewOperation": "A String", # The name of the operation triggered by the processed document. This field is populated only when the [state] is [HUMAN_REVIEW_IN_PROGRESS]. It has the same response type and metadata as the long running operation returned by [ReviewDocument] method.
"state": "A String", # The state of human review on the processing request.
"stateMessage": "A String", # A message providing more details about the human review state.
},
}</pre>
</div>
<div class="method">
<code class="details" id="setDefaultProcessorVersion">setDefaultProcessorVersion(processor, body=None, x__xgafv=None)</code>
<pre>Set the default (active) version of a Processor that will be used in ProcessDocument and BatchProcessDocuments.
Args:
processor: string, Required. The resource name of the Processor to change default version. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for the set default processor version method.
"defaultProcessorVersion": "A String", # Required. The resource name of child ProcessorVersion to use as default.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
</body></html>
|
