Skip to content
Snippets Groups Projects
Commit 7ac8ee6e authored by Bastien Abadie's avatar Bastien Abadie
Browse files

Merge branch 'save_entity_in_transcription' into 'master' 

link entity to transcription

See merge request !347
parents 19517c8f 240c46e2
No related branches found
No related tags found
1 merge request!347link entity to transcription
Expand all Hide whitespace changes
Inline Side-by-side
Showing
with 291 additions and 584 deletions
arkindex/documents/api/ml.py
+ 2
− 2
View file @ 7ac8ee6e
......@@ -195,9 +195,9 @@ class PageXmlTranscriptionsImport(CreateModelMixin, APIView):
except AssertionError as e:
raise ValidationError('Could not parse PAGE XML document: {!s}'.format(e))
parser.save_transcriptions(page)
transcriptions = parser.save_transcriptions(page)
blocks = parser.create_blocks()
blocks = parser.create_blocks(transcriptions)
blocks = parser.merge(blocks)
path = os.path.join(settings.BASE_DIR, 'documents', 'fixtures', 'roles_transkribus.yml')
......
arkindex/documents/pagexml.py
+ 24
− 7
View file @ 7ac8ee6e
......@@ -5,7 +5,7 @@ from arkindex_common.pagexml import PageXmlPage
from arkindex_common.enums import MetaType
from arkindex.project.polygon import Polygon
from arkindex.documents.models import DataSource, TranscriptionType, ElementType, Page, Transcription,\
Entity, EntityRole, EntityLink, MetaData
Entity, EntityRole, EntityLink, MetaData, TranscriptionEntity
from arkindex.documents.indexer import Indexer
import functools
import Levenshtein
......@@ -118,10 +118,13 @@ class PageXmlParser(object):
logger.warning('No transcriptions to save')
return
region_count, line_count, region_ts_count, line_ts_count = 0, 0, 0, 0
transcriptions = []
for region in self.pagexml_page.page.text_regions:
region_count += 1
_, created = self.create_transcription(region, page, type=TranscriptionType.Paragraph)
paragraph, created = self.create_transcription(region, page, type=TranscriptionType.Paragraph)
region_ts_count += created
if paragraph:
transcriptions.append((paragraph.id, region))
for line in region.lines:
line_count += 1
_, created = self.create_transcription(line, page)
......@@ -133,6 +136,7 @@ class PageXmlParser(object):
line_ts_count,
))
self.index(page)
return transcriptions
def merge(self, blocks):
"""
......@@ -263,12 +267,14 @@ class PageXmlParser(object):
def create_objects(self, blocks, page, path, types, ratio=0.90):
"""
Create entity, role and link
Create entity on transcription, role and link
"""
entities = []
for tags in blocks.values():
new_entities, new_tags = self.create_entities(tags, page, types, ratio)
entities += new_entities
self.create_link_transcription_entity(new_tags)
tags = self.create_roles(new_tags, page, path, ratio)
self.create_links(tags, page, path, ratio)
return entities
......@@ -323,6 +329,16 @@ class PageXmlParser(object):
tag['entity_id'] = entity.id
return entities, tags
def create_link_transcription_entity(self, tags):
for tag in tags:
if'entity_id' in tag.keys() and 'transcription_id' in tag.keys():
TranscriptionEntity.objects.get_or_create(
entity_id=tag['entity_id'],
transcription_id=tag['transcription_id'],
offset=tag['offset_in_region'],
length=tag['length']
)
def create_roles(self, tags, page, path, ratio):
"""
Create role according to '_role' in tag
......@@ -386,24 +402,25 @@ class PageXmlParser(object):
)
return tags
def create_blocks(self):
def create_blocks(self, transcriptions):
"""
Create blocks with lines, and line with tags
Order tags according to 'offset'
Order lines and blocks according to 'reading_order'
"""
def update_tag(tag, line, index):
def update_tag(tag, line, index, transcription_id):
if 'offset' in tag.keys():
# Save the text value
tag['value'] = line.text[
int(tag['offset']):int(tag['length'])+int(tag['offset'])
] if line.text else ''
tag['reading_order'] = index
tag['transcription_id'] = transcription_id
return tag
blocks = []
for region in self.pagexml_page.page.text_regions:
for transcription_id, region in transcriptions:
# Search the tag 'readingOrder' to select the index
tag_reading_order = next(filter(lambda tag: tag.name == 'readingOrder', region.tags))
index_region = int(tag_reading_order.index)
......@@ -423,7 +440,7 @@ class PageXmlParser(object):
}
# Add all tags
tags = [
update_tag(tag.as_dict(), line, index_line)
update_tag(tag.as_dict(), line, index_line, transcription_id)
for tag in line.tags
]
current_line['tags'] = tags
......
arkindex/documents/tests/pagexml_samples/first_and_last_name.xml
+ 16
− 48
View file @ 7ac8ee6e
......@@ -130,87 +130,55 @@ T.O.N. PtreCuré</Unicode>
</TextRegion>
<TextRegion orientation="0.0" id="TextRegion_1552403880332_1857" custom="readingOrder {index:1;}">
<Coords points="547,813 701,813 1324,819 1576,823 2079,799 2334,808 2334,1644 2063,1650 1883,1654 1454,1642 1010,1650 766,1656 559,1660 547,1655"/>
<TextLine id="r2l9" custom="readingOrder {index:0;} _date {offset:3; length:35;_enregistrement:1;} textStyle {offset:13; length:7;strikethrough:true; fontSize:0.0; kerning:0;} strike_through {offset:13; length:7;}">
<Coords points="570,898 655,900 741,900 826,900 912,900 997,900 1083,898 1168,898 1254,897 1339,895 1425,894 1510,892 1596,891 1681,891 1767,889 1852,888 1938,888 2023,888 2109,886 2194,887 2316,904 2316,847 2194,830 2109,829 2023,831 1938,831 1852,831 1767,832 1681,834 1596,834 1510,835 1425,837 1339,838 1254,840 1168,841 1083,841 997,843 912,843 826,843 741,843 655,843 570,841"/>
<Baseline points="570,879 655,881 741,881 826,881 912,881 997,881 1083,879 1168,879 1254,878 1339,876 1425,875 1510,873 1596,872 1681,872 1767,870 1852,869 1938,869 2023,869 2109,867 2194,868 2315,886"/>
<TextEquiv>
<Unicode>Le vingt-six juillet mil neuf cent-six,</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l10" custom="readingOrder {index:1;}">
<Coords points="590,986 671,987 753,987 834,987 916,989 998,989 1079,989 1161,989 1242,989 1324,989 1406,987 1487,987 1569,986 1650,984 1732,984 1814,983 1895,981 1977,980 2058,977 2140,975 2222,974 2222,911 2140,912 2058,914 1977,917 1895,918 1814,920 1732,921 1650,921 1569,923 1487,924 1406,924 1324,926 1242,926 1161,926 1079,926 998,926 916,926 834,924 753,924 671,924 590,923"/>
<Baseline points="590,965 671,966 753,966 834,966 916,968 998,968 1079,968 1161,968 1242,968 1324,968 1406,966 1487,966 1569,965 1650,963 1732,963 1814,962 1895,960 1977,959 2058,956 2140,954 2222,953"/>
<TextEquiv>
<Unicode>nous Prêtré Curé soussigné, avons</Unicode>
<Unicode>Nous avons</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l11" custom="readingOrder {index:2;}">
<Coords points="566,1090 651,1089 736,1086 822,1084 907,1083 992,1081 1078,1080 1163,1080 1248,1078 1334,1078 1419,1077 1504,1077 1590,1077 1675,1075 1760,1075 1846,1075 1931,1075 2016,1074 2102,1074 2187,1074 2273,1072 2273,1006 2187,1008 2102,1008 2016,1008 1931,1009 1846,1009 1760,1009 1675,1009 1590,1011 1504,1011 1419,1011 1334,1012 1248,1012 1163,1014 1078,1014 992,1015 907,1017 822,1018 736,1020 651,1023 566,1024"/>
<Baseline points="566,1068 651,1067 736,1064 822,1062 907,1061 992,1059 1078,1058 1163,1058 1248,1056 1334,1056 1419,1055 1504,1055 1590,1055 1675,1053 1760,1053 1846,1053 1931,1053 2016,1052 2102,1052 2187,1052 2273,1050"/>
<TextEquiv>
<Unicode>inhumé dans le cimetière de cette paroisse</Unicode>
<Unicode>inhumé</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l12" custom="readingOrder {index:3;} _prenom {offset:14; length:6;_role:sujet;} _date {offset:35; length:11;_evenement:1;} unclear {offset:38; length:8;}">
<TextLine id="r2l12" custom="readingOrder {index:3;} _prenom {offset:14; length:6;_role:sujet;}">
<Coords points="554,1185 641,1185 728,1185 816,1183 903,1183 991,1182 1078,1180 1166,1179 1253,1177 1341,1176 1428,1174 1515,1173 1603,1171 1690,1170 1778,1170 1865,1168 1953,1168 2040,1168 2128,1168 2215,1168 2303,1170 2303,1104 2215,1102 2128,1102 2040,1102 1953,1102 1865,1102 1778,1104 1690,1104 1603,1105 1515,1107 1428,1108 1341,1110 1253,1111 1166,1113 1078,1114 991,1116 903,1117 816,1117 728,1119 641,1119 554,1119"/>
<Baseline points="554,1163 641,1163 728,1163 816,1161 903,1161 991,1160 1078,1158 1166,1157 1253,1155 1341,1154 1428,1152 1515,1151 1603,1149 1690,1148 1778,1148 1865,1146 1953,1146 2040,1146 2128,1146 2215,1146 2303,1148"/>
<TextEquiv>
<Unicode>le corps d'un garçon mort-né, issu aujourd'hui</Unicode>
<Unicode>le corps d'un garçon issu</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l13" custom="readingOrder {index:4;} _prenom {offset:23; length:6;_role:père;} _nom {offset:30; length:3; continued:true;}">
<TextLine id="r2l13" custom="readingOrder {index:4;} _prenom {offset:3; length:6;_role:père;} _nom {offset:10; length:3; continued:true;}">
<Coords points="576,1273 659,1273 743,1273 827,1273 911,1272 995,1272 1078,1272 1162,1270 1246,1269 1330,1269 1414,1267 1497,1266 1581,1264 1665,1263 1749,1263 1833,1261 1916,1260 2000,1258 2084,1255 2168,1254 2252,1252 2252,1186 2168,1188 2084,1189 2000,1192 1916,1194 1833,1195 1749,1197 1665,1197 1581,1198 1497,1200 1414,1201 1330,1203 1246,1203 1162,1204 1078,1206 995,1206 911,1206 827,1207 743,1207 659,1207 576,1207"/>
<Baseline points="576,1251 659,1251 743,1251 827,1251 911,1250 995,1250 1078,1250 1162,1248 1246,1247 1330,1247 1414,1245 1497,1244 1581,1242 1665,1241 1749,1241 1833,1239 1916,1238 2000,1236 2084,1233 2168,1232 2252,1230"/>
<TextEquiv>
<Unicode>du légitime mariage de Joseph Du-</Unicode>
<Unicode>de Joseph Du-</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l14" custom="readingOrder {index:5;} _nom {offset:0; length:6; continued:true;} _profession {offset:8; length:8;} _lieu_residence {offset:20; length:14;}">
<TextLine id="r2l14" custom="readingOrder {index:5;} _nom {offset:0; length:6; continued:true;}">
<Coords points="551,1374 635,1369 719,1366 803,1363 887,1360 971,1359 1055,1359 1140,1357 1224,1357 1308,1357 1392,1357 1476,1357 1560,1357 1644,1356 1729,1356 1813,1354 1897,1353 1981,1351 2065,1348 2149,1344 2234,1339 2234,1272 2149,1277 2065,1281 1981,1284 1897,1286 1813,1287 1729,1289 1644,1289 1560,1290 1476,1290 1392,1290 1308,1290 1224,1290 1140,1290 1055,1292 971,1292 887,1293 803,1296 719,1299 635,1302 551,1307"/>
<Baseline points="551,1352 635,1347 719,1344 803,1341 887,1338 971,1337 1055,1337 1140,1335 1224,1335 1308,1335 1392,1335 1476,1335 1560,1335 1644,1334 1729,1334 1813,1332 1897,1331 1981,1329 2065,1326 2149,1322 2234,1317"/>
<TextEquiv>
<Unicode>moulin, forgeron de cette paroisse, et </Unicode>
<Unicode>moulin, et </Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l15" custom="readingOrder {index:6;} _prenom {offset:3; length:6;_role:mère;} _nom {offset:10; length:8;} _prenom {offset:29; length:6;_role:témoin;} _nom {offset:36; length:3; continued:true;}">
<TextLine id="r2l15" custom="readingOrder {index:6;} _prenom {offset:3; length:6;_role:mère;} _nom {offset:10; length:8;}">
<Coords points="569,1455 655,1456 741,1458 827,1459 914,1459 1000,1459 1086,1459 1172,1459 1259,1459 1345,1458 1431,1458 1517,1456 1604,1455 1690,1453 1776,1452 1862,1450 1949,1449 2035,1447 2121,1446 2207,1444 2294,1443 2294,1377 2207,1378 2121,1380 2035,1381 1949,1383 1862,1384 1776,1386 1690,1387 1604,1389 1517,1390 1431,1392 1345,1392 1259,1393 1172,1393 1086,1393 1000,1393 914,1393 827,1393 741,1392 655,1390 569,1389"/>
<Baseline points="569,1433 655,1434 741,1436 827,1437 914,1437 1000,1437 1086,1437 1172,1437 1259,1437 1345,1436 1431,1436 1517,1434 1604,1433 1690,1431 1776,1430 1862,1428 1949,1427 2035,1425 2121,1424 2207,1422 2294,1421"/>
<TextEquiv>
<Unicode>de Valeda Paquette. Témoins, Joseph Du-</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l16" custom="readingOrder {index:7;} _nom {offset:0; length:6; continued:true;} textStyle {offset:25; length:1;fontSize:0.0; kerning:0; superscript:true;}">
<Coords points="548,1561 629,1556 711,1553 793,1550 875,1548 956,1546 1038,1544 1120,1544 1202,1543 1283,1543 1365,1541 1447,1541 1529,1541 1610,1541 1692,1541 1774,1540 1856,1540 1937,1539 2019,1538 2101,1537 2183,1534 2183,1473 2101,1476 2019,1477 1937,1478 1856,1479 1774,1479 1692,1480 1610,1480 1529,1480 1447,1480 1365,1480 1283,1482 1202,1482 1120,1483 1038,1483 956,1485 875,1487 793,1489 711,1492 629,1495 548,1500"/>
<Baseline points="548,1541 629,1536 711,1533 793,1530 875,1528 956,1526 1038,1524 1120,1524 1202,1523 1283,1523 1365,1521 1447,1521 1529,1521 1610,1521 1692,1521 1774,1520 1856,1520 1937,1519 2019,1518 2101,1517 2183,1514"/>
<TextEquiv>
<Unicode>moulin, le père sus-dit. v mot rayé nul;</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="line_1552403744720_1799" custom="readingOrder {index:8;}">
<Coords points="560,1614 634,1608 709,1604 784,1600 858,1598 933,1596 1008,1595 1082,1594 1157,1593 1232,1593 1307,1591 1324,1591 1324,1621 1307,1621 1232,1623 1157,1623 1082,1624 1008,1625 933,1626 858,1628 784,1630 709,1634 634,1638 560,1644"/>
<Baseline points="560,1634 634,1628 709,1624 784,1620 858,1618 933,1616 1008,1615 1082,1614 1157,1613 1232,1613 1307,1611 1324,1611"/>
<TextEquiv>
<Unicode>mot en marge bon.</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="line_1553864210171_292" custom="readingOrder {index:9;} structure {type:signature-mark;} textStyle {offset:12; length:4;underlined:true; fontSize:0.0; kerning:0; superscript:true;} textStyle {offset:16; length:4;fontSize:0.0; kerning:0; subscript:true;}">
<Coords points="1366,1568 1527,1568 1661,1566 1738,1564 1783,1564 1853,1562 1904,1560 1969,1553 2038,1571 2112,1570 2240,1558 2244,1608 2114,1614 2029,1626 1966,1610 1908,1614 1851,1612 1784,1614 1739,1614 1662,1616 1527,1618 1366,1618"/>
<Baseline points="1366,1613 1527,1613 1662,1611 1739,1609 1784,1609 1851,1607 1894,1607 1966,1598 2028,1614 2115,1603 2244,1599"/>
<TextEquiv>
<Unicode>Thos. O'NeilPtreCuré</Unicode>
<Unicode>de Valeda Paquette.</Unicode>
</TextEquiv>
</TextLine>
<TextEquiv>
<Unicode>Le vingt-six juillet mil neuf cent-six,
nous Prêtré Curé soussigné, avons
inhumé dans le cimetière de cette paroisse
le corps d'un garçon mort-né, issu aujourd'hui
du légitime mariage de Joseph Du-
moulin, forgeron de cette paroisse, et
de Valeda Paquette. Témoins, Joseph Du-
moulin, le père sus-dit. v mot rayé nul;
mot en marge bon.
Thos. O'NeilPtreCuré</Unicode>
<Unicode>Nous avons
inhumé
le corps d'un garçon issu
de Joseph Du-
moulin, et
de Valeda Paquette.</Unicode>
</TextEquiv>
</TextRegion>
</Page>
......
arkindex/documents/tests/pagexml_samples/merge.xml
+ 10
− 10
View file @ 7ac8ee6e
......@@ -74,25 +74,25 @@ P.108</Unicode>
<Unicode>prêtre curé soussigné, avons baptisé</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l3" custom="readingOrder {index:2;} _prenom {offset:0; length:19;_role:sujet;} _date {offset:32; length:11;_evenement:1;}">
<TextLine id="r2l3" custom="readingOrder {index:2;} _prenom {offset:0; length:19;_role:sujet;}">
<Coords points="596,516 682,518 769,520 856,522 943,523 1030,523 1117,523 1203,523 1290,522 1377,522 1464,520 1551,520 1638,519 1725,517 1811,516 1898,516 1985,514 2072,514 2159,514 2246,514 2351,516 2351,450 2246,448 2159,448 2072,448 1985,448 1898,450 1811,450 1725,451 1638,453 1551,454 1464,454 1377,456 1290,456 1203,457 1117,457 1030,457 943,457 856,456 769,454 682,452 596,450"/>
<Baseline points="596,494 682,496 769,498 856,500 943,501 1030,501 1117,501 1203,501 1290,500 1377,500 1464,498 1551,498 1638,497 1725,495 1811,494 1898,494 1985,492 2072,492 2159,492 2246,492 2350,494"/>
<TextEquiv>
<Unicode>Marie-Alice-Rosilda, fille, née aujourd'hui</Unicode>
<Unicode>Marie-Alice-Rosilda, née</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l4" custom="readingOrder {index:3;} _prenom {offset:23; length:7;_role:père;} _nom {offset:31; length:6;}">
<TextLine id="r2l4" custom="readingOrder {index:3;} _prenom {offset:3; length:7;_role:père;} _nom {offset:11; length:6;}">
<Coords points="579,610 666,613 753,615 840,616 927,616 1014,616 1101,616 1188,615 1275,615 1362,613 1449,612 1536,611 1623,610 1710,609 1797,607 1884,606 1971,606 2058,606 2145,606 2232,606 2333,607 2333,540 2232,539 2145,539 2058,539 1971,539 1884,539 1797,540 1710,542 1623,543 1536,544 1449,545 1362,546 1275,548 1188,548 1101,549 1014,549 927,549 840,549 753,548 666,546 579,543"/>
<Baseline points="579,588 666,591 753,593 840,594 927,594 1014,594 1101,594 1188,593 1275,593 1362,591 1449,590 1536,589 1623,588 1710,587 1797,585 1884,584 1971,584 2058,584 2145,584 2232,584 2333,586"/>
<TextEquiv>
<Unicode>du légitime mariage de Antoine Landry</Unicode>
<Unicode>de Antoine Landry</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l5" custom="readingOrder {index:4;} _lieu_residence {offset:12; length:14;} _prenom {offset:34; length:6;_role:mère;}">
<TextLine id="r2l5" custom="readingOrder {index:4;} _prenom {offset:6; length:6;_role:mère;}">
<Coords points="579,703 665,705 751,706 838,708 924,709 1011,709 1097,709 1183,709 1270,708 1356,708 1443,708 1529,706 1615,706 1702,705 1788,705 1875,705 1961,705 2047,705 2134,706 2220,708 2307,709 2307,642 2220,641 2134,639 2047,638 1961,638 1875,638 1788,638 1702,638 1615,639 1529,639 1443,641 1356,641 1270,641 1183,642 1097,642 1011,642 924,642 838,641 751,639 665,638 579,636"/>
<Baseline points="579,681 665,683 751,684 838,686 924,687 1011,687 1097,687 1183,687 1270,686 1356,686 1443,686 1529,684 1615,684 1702,683 1788,683 1875,683 1961,683 2047,683 2134,684 2220,686 2307,687"/>
<TextEquiv>
<Unicode>habitant de cette paroisse, et de Zelpha</Unicode>
<Unicode>et de Zelpha</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l6" custom="readingOrder {index:5;} _nom {offset:0; length:10;}">
......@@ -104,10 +104,10 @@ P.108</Unicode>
</TextLine>
<TextEquiv>
<Unicode>Nous
prêtre curé soussigné, avons baptisé
Marie-Alice-Rosilda, née aujourd'hui
du légitime mariage de Antoine Landry
habitant de cette paroisse, et de Zelpha
avons baptisé
Marie-Alice-Rosilda, née
de Antoine Landry
et de Zelpha
Beauchesne.</Unicode>
</TextEquiv>
</TextRegion>
......
arkindex/documents/tests/pagexml_samples/regroup.xml
+ 17
− 95
View file @ 7ac8ee6e
......@@ -60,128 +60,50 @@ Elmire</Unicode>
</TextRegion>
<TextRegion orientation="0.0" id="TextRegion_1552403626791_1738" custom="readingOrder {index:0;}">
<Coords points="512,90 2318,88 2318,1435 512,1437"/>
<TextLine id="r2l1" custom="readingOrder {index:0;} structure {type:page-number;}">
<Coords points="1475,168 1501,169 1527,169 1553,171 1579,171 1606,170 1632,169 1658,168 1684,167 1710,165 1737,163 1763,162 1789,160 1815,159 1841,157 1868,157 1894,156 1920,155 1946,154 1973,154 1973,88 1946,88 1920,89 1894,90 1868,91 1841,91 1815,93 1789,94 1763,96 1737,97 1710,99 1684,101 1658,102 1632,103 1606,104 1579,105 1553,105 1527,103 1501,103 1475,102"/>
<Baseline points="1475,146 1501,147 1527,147 1553,149 1579,149 1606,148 1632,147 1658,146 1684,145 1710,143 1737,141 1763,140 1789,138 1815,137 1841,135 1868,135 1894,134 1920,133 1946,132 1973,132"/>
<TextEquiv>
<Unicode>Neuvième feuillet</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l6" custom="readingOrder {index:5;} _profession {offset:0; length:10;} _lieu_residence {offset:14; length:14;} _prenom {offset:36; length:5; continued:true;_role:mère;}">
<TextLine id="r2l6" custom="readingOrder {index:3;} _prenom {offset:6; length:5; continued:true;_role:mère;}">
<Coords points="509,730 595,729 682,727 769,726 855,724 942,723 1029,723 1115,721 1202,721 1289,720 1376,720 1462,718 1549,718 1636,717 1722,715 1809,715 1896,714 1982,712 2069,711 2156,708 2243,706 2243,640 2156,642 2069,645 1982,646 1896,648 1809,649 1722,649 1636,651 1549,652 1462,652 1376,654 1289,654 1202,655 1115,655 1029,657 942,657 855,658 769,660 682,661 595,663 509,664"/>
<Baseline points="509,708 595,707 682,705 769,704 855,702 942,701 1029,701 1115,699 1202,699 1289,698 1376,698 1462,696 1549,696 1636,695 1722,693 1809,693 1896,692 1982,690 2069,689 2156,686 2243,684"/>
<TextEquiv>
<Unicode>journalier de cette paroisse, et de Ermi-</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l2" custom="readingOrder {index:1;} _date {offset:3; length:29;_enregistrement:1;}">
<Coords points="486,333 567,334 649,336 730,336 812,336 893,336 975,336 1056,334 1138,334 1219,333 1301,331 1383,330 1464,328 1546,328 1627,327 1709,325 1790,324 1872,324 1953,322 2035,322 2117,322 2117,256 2035,256 1953,256 1872,258 1790,258 1709,259 1627,261 1546,262 1464,262 1383,264 1301,265 1219,267 1138,268 1056,268 975,270 893,270 812,270 730,270 649,270 567,268 486,267"/>
<Baseline points="486,311 567,312 649,314 730,314 812,314 893,314 975,314 1056,312 1138,312 1219,311 1301,309 1383,308 1464,306 1546,306 1627,305 1709,303 1790,302 1872,302 1953,300 2035,300 2117,300"/>
<TextEquiv>
<Unicode>Le quinze juin mil neuf cent six</Unicode>
<Unicode>et de Ermi-</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l4" custom="readingOrder {index:3;} _prenom {offset:5; length:13;_role:sujet;} _date {offset:31; length:4;_evenement:1;}">
<TextLine id="r2l4" custom="readingOrder {index:1;} _prenom {offset:5; length:13;_role:sujet;}">
<Coords points="527,524 614,525 702,528 790,530 878,531 966,531 1053,531 1141,531 1229,530 1317,530 1405,528 1492,527 1580,524 1668,522 1756,521 1844,518 1931,516 2019,513 2107,511 2195,509 2283,507 2283,443 2195,445 2107,447 2019,449 1931,452 1844,454 1756,457 1668,458 1580,460 1492,463 1405,464 1317,466 1229,466 1141,467 1053,467 966,467 878,467 790,466 702,464 614,461 527,460"/>
<Baseline points="527,503 614,504 702,507 790,509 878,510 966,510 1053,510 1141,510 1229,509 1317,509 1405,507 1492,506 1580,503 1668,501 1756,500 1844,497 1931,495 2019,492 2107,490 2195,488 2283,486"/>
<TextEquiv>
<Unicode>tisé Marie-Evilina, fille, née hier du</Unicode>
<Unicode>tisé Marie-Evilina, fille de</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l5" custom="readingOrder {index:4;} _prenom {offset:20; length:7;_role:père;} _nom {offset:28; length:9;}">
<TextLine id="r2l5" custom="readingOrder {index:2;} _prenom {offset:0; length:7;_role:père;} _nom {offset:8; length:9;}">
<Coords points="510,635 598,632 687,629 776,626 865,624 953,622 1042,620 1131,620 1220,618 1308,617 1397,617 1486,615 1575,615 1663,614 1752,614 1841,612 1930,611 2018,609 2107,608 2196,606 2285,603 2285,539 2196,542 2107,544 2018,545 1930,547 1841,548 1752,550 1663,550 1575,551 1486,551 1397,553 1308,553 1220,554 1131,556 1042,556 953,558 865,560 776,562 687,565 598,568 510,571"/>
<Baseline points="510,614 598,611 687,608 776,605 865,603 953,601 1042,599 1131,599 1220,597 1308,596 1397,596 1486,594 1575,594 1663,593 1752,593 1841,591 1930,590 2018,588 2107,587 2196,585 2285,582"/>
<TextEquiv>
<Unicode>légitime mariage de Camille Thibeault</Unicode>
<Unicode>Camille Thibeault</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l7" custom="readingOrder {index:6;} _prenom {offset:0; length:4; continued:true;_role:mère;} _nom {offset:5; length:8;} _prenom {offset:24; length:6;_role:parrain;} _nom {offset:31; length:9;}">
<TextLine id="r2l7" custom="readingOrder {index:4;} _prenom {offset:0; length:4; continued:true;_role:mère;} _nom {offset:5; length:8;}">
<Coords points="497,825 586,826 676,828 766,828 856,828 946,827 1036,826 1125,825 1215,823 1305,820 1395,819 1485,816 1575,814 1665,811 1754,810 1844,807 1934,805 2024,804 2114,801 2204,801 2294,799 2294,733 2204,735 2114,735 2024,738 1934,739 1844,741 1754,744 1665,745 1575,748 1485,750 1395,753 1305,754 1215,757 1125,759 1036,760 946,761 856,762 766,762 676,762 586,760 497,759"/>
<Baseline points="497,803 586,804 676,806 766,806 856,806 946,805 1036,804 1125,803 1215,801 1305,798 1395,797 1485,794 1575,792 1665,789 1754,788 1844,785 1934,783 2024,782 2114,779 2204,779 2294,777"/>
<TextEquiv>
<Unicode>nise Champeau. Parrain, Alfred Thibeault</Unicode>
<Unicode>nise Champeau.</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l3" custom="readingOrder {index:2;}">
<TextLine id="r2l3" custom="readingOrder {index:0;}">
<Coords points="512,432 599,432 686,432 773,432 861,432 948,430 1035,430 1123,429 1210,427 1297,426 1385,425 1472,424 1559,423 1646,422 1734,421 1821,421 1908,420 1996,420 2083,421 2170,421 2272,423 2272,357 2170,355 2083,355 1996,354 1908,354 1821,355 1734,355 1646,356 1559,357 1472,358 1385,359 1297,360 1210,361 1123,363 1035,364 948,364 861,366 773,366 686,366 599,366 512,366"/>
<Baseline points="512,410 599,410 686,410 773,410 861,410 948,408 1035,408 1123,407 1210,405 1297,404 1385,403 1472,402 1559,401 1646,400 1734,399 1821,399 1908,398 1996,398 2083,399 2170,399 2274,404"/>
<TextEquiv>
<Unicode>nous prêtre curé soussigné, avons bap-</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l8" custom="readingOrder {index:7;} _profession {offset:0; length:10;} _lieu_residence {offset:14; length:14;}">
<Coords points="530,915 618,915 707,916 795,916 884,916 972,918 1061,918 1149,916 1238,916 1326,916 1415,915 1503,914 1592,913 1680,911 1769,910 1857,907 1946,905 2034,903 2123,900 2211,896 2300,892 2300,826 2211,830 2123,834 2034,837 1946,839 1857,841 1769,844 1680,845 1592,847 1503,848 1415,849 1326,850 1238,850 1149,850 1061,852 972,852 884,850 795,850 707,850 618,849 530,849"/>
<Baseline points="530,893 618,893 707,894 795,894 884,894 972,896 1061,896 1149,894 1238,894 1326,894 1415,893 1503,892 1592,891 1680,889 1769,888 1857,885 1946,883 2034,881 2123,878 2211,874 2300,870"/>
<TextEquiv>
<Unicode>journalier de cette paroisse et oncle de l'en-</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l9" custom="readingOrder {index:8;} _prenom {offset:28; length:6;_role:marraine;}">
<Coords points="513,995 599,999 686,1003 773,1007 860,1008 947,1010 1034,1010 1120,1010 1207,1010 1294,1009 1381,1008 1468,1007 1555,1004 1642,1002 1728,1001 1815,999 1902,997 1989,996 2076,995 2163,993 2250,993 2250,929 2163,929 2076,931 1989,932 1902,933 1815,935 1728,937 1642,938 1555,940 1468,943 1381,944 1294,945 1207,946 1120,946 1034,946 947,946 860,944 773,943 686,939 599,935 513,931"/>
<Baseline points="513,974 599,978 686,982 773,986 860,987 947,989 1034,989 1120,989 1207,989 1294,988 1381,987 1468,986 1555,983 1642,981 1728,980 1815,978 1902,976 1989,975 2076,974 2163,972 2250,972"/>
<TextEquiv>
<Unicode>fant, marraine, son épouse, Valeda</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l10" custom="readingOrder {index:9;} _nom {offset:0; length:7;}">
<Coords points="509,1091 595,1092 681,1095 767,1097 854,1097 940,1098 1026,1098 1113,1098 1199,1097 1285,1097 1372,1095 1458,1094 1544,1094 1630,1092 1717,1091 1803,1089 1889,1089 1976,1088 2062,1088 2148,1088 2235,1088 2235,1024 2148,1024 2062,1024 1976,1024 1889,1025 1803,1025 1717,1027 1630,1028 1544,1030 1458,1030 1372,1031 1285,1033 1199,1033 1113,1034 1026,1034 940,1034 854,1033 767,1033 681,1031 595,1028 509,1027"/>
<Baseline points="509,1070 595,1071 681,1074 767,1076 854,1076 940,1077 1026,1077 1113,1077 1199,1076 1285,1076 1372,1074 1458,1073 1544,1073 1630,1071 1717,1070 1803,1068 1889,1068 1976,1067 2062,1067 2148,1067 2235,1067"/>
<TextEquiv>
<Unicode>Chaloux, lesquels, ainsi que le père</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l11" custom="readingOrder {index:10;}">
<Coords points="525,1188 609,1189 693,1191 777,1192 862,1192 946,1192 1030,1191 1115,1191 1199,1189 1283,1188 1368,1188 1452,1186 1536,1185 1620,1185 1705,1183 1789,1183 1873,1183 1958,1185 2042,1186 2126,1188 2211,1192 2211,1126 2126,1122 2042,1120 1958,1119 1873,1117 1789,1117 1705,1117 1620,1119 1536,1119 1452,1120 1368,1122 1283,1122 1199,1123 1115,1125 1030,1125 946,1126 862,1126 777,1126 693,1125 609,1123 525,1122"/>
<Baseline points="525,1166 609,1167 693,1169 777,1170 862,1170 946,1170 1030,1169 1115,1169 1199,1167 1283,1166 1368,1166 1452,1164 1536,1163 1620,1163 1705,1161 1789,1161 1873,1161 1958,1163 2042,1164 2126,1166 2211,1170"/>
<TextEquiv>
<Unicode>ont signé avec nous : lecture faite</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="line_1552403563188_1681" custom="readingOrder {index:12;} structure {type:signature-mark;}">
<Coords points="1420,1217 1482,1216 1560,1216 1637,1215 1715,1215 1792,1213 1869,1210 1947,1208 2024,1206 2102,1203 2102,1269 2024,1272 1947,1274 1869,1276 1792,1279 1715,1281 1637,1281 1560,1282 1482,1282 1420,1283"/>
<Baseline points="1420,1261 1482,1260 1560,1260 1637,1259 1715,1259 1792,1257 1869,1254 1947,1252 2024,1250 2102,1247"/>
<TextEquiv>
<Unicode>Alf. Thib ault</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l14" custom="readingOrder {index:13;} structure {type:signature-mark;}">
<Coords points="573,1362 610,1364 648,1366 686,1368 723,1368 761,1370 799,1370 836,1370 874,1370 912,1370 950,1370 987,1368 1025,1368 1063,1367 1100,1367 1138,1367 1176,1365 1213,1365 1251,1365 1289,1365 1327,1365 1328,1320 1290,1320 1253,1319 1215,1319 1177,1320 1139,1322 1101,1319 1064,1319 1025,1320 987,1320 950,1320 912,1320 876,1320 838,1320 801,1320 763,1320 724,1319 687,1319 649,1319 611,1317 575,1318"/>
<Baseline points="572,1353 609,1355 647,1357 685,1359 722,1359 760,1361 798,1361 835,1361 873,1361 911,1361 949,1361 986,1359 1024,1359 1062,1358 1099,1358 1137,1358 1175,1356 1212,1356 1250,1356 1288,1356 1326,1356"/>
<TextEquiv>
<Unicode>Valeda Chaloux</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="line_1552403564619_1686" custom="readingOrder {index:11;} structure {type:signature-mark;}">
<Coords points="554,1221 631,1220 708,1219 786,1219 863,1218 1347,1218 1347,1284 863,1284 786,1285 708,1285 631,1286 554,1287"/>
<Baseline points="554,1265 631,1264 708,1263 786,1263 863,1262 941,1262 1018,1262 1095,1262 1173,1262 1250,1262 1328,1262 1347,1262"/>
<TextEquiv>
<Unicode>Camille Thibeault</Unicode>
</TextEquiv>
</TextLine>
<TextLine id="r2l15" custom="readingOrder {index:14;} structure {type:signature-mark;} textStyle {offset:13; length:4;underlined:true; fontSize:0.0; kerning:0; superscript:true;} textStyle {offset:17; length:4;fontSize:0.0; kerning:0; subscript:true;}">
<Coords points="1235,1421 1280,1421 1326,1422 1372,1422 1418,1422 1463,1424 1509,1424 1555,1422 1601,1422 1646,1422 1692,1422 1738,1421 1784,1421 1829,1420 1875,1419 1921,1418 1967,1418 2012,1416 2058,1416 2104,1415 2150,1415 2150,1367 2104,1367 2060,1367 2014,1367 1968,1367 1922,1367 1875,1367 1829,1368 1787,1369 1741,1369 1695,1369 1649,1369 1604,1367 1558,1367 1509,1367 1463,1367 1420,1368 1374,1368 1330,1370 1284,1369 1236,1369"/>
<Baseline points="1235,1409 1280,1409 1326,1410 1372,1410 1418,1410 1463,1412 1509,1412 1555,1410 1601,1410 1646,1410 1692,1410 1738,1409 1784,1409 1829,1408 1875,1407 1921,1406 1967,1406 2012,1404 2058,1404 2104,1403 2150,1403"/>
<TextEquiv>
<Unicode>Thos. O'Neil Ptrecuré</Unicode>
<Unicode>Nous avons bap-</Unicode>
</TextEquiv>
</TextLine>
<TextEquiv>
<Unicode>Neuvième feuillet
Le quinze juin mil neuf cent six
nous prêtre curé soussigné, avons bap-
tisé Marie-Evilina, fille, née hier du
légitime mariage de Camille Thibeault
journalier de cette paroisse, et de Ermi-
nise Champeau. Parrain, Alfred Thibeault
journalier de cette paroisse et oncle de l'en-
fant, marraine, son épouse, Valeda
Chaloux, lesquels, ainsi que le père
ont signé avec nous : lecture faite
<Unicode>Nous avons bap-
tisé Marie-Evilina, fille de
Camille Thibeault
Alf. Thib ault
Valeda Chaloux
Thos. O'Neil Ptrecuré</Unicode>
et de Ermi-
nise Champeau.
</Unicode>
</TextEquiv>
</TextRegion>
</Page>
......
arkindex/documents/tests/test_pagexml.py
+ 222
− 422
View file @ 7ac8ee6e
This diff is collapsed.
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment