tei2teiHM.py
| 1 |
#!/usr/bin/python
|
|---|---|
| 2 |
# -*- coding: utf-8 -*-
|
| 3 |
|
| 4 |
#import xlrd
|
| 5 |
#import pandas as pd
|
| 6 |
import os |
| 7 |
import re |
| 8 |
import unicodedata |
| 9 |
import sys |
| 10 |
import csv |
| 11 |
import xml.etree.ElementTree as ET |
| 12 |
import prettify |
| 13 |
|
| 14 |
from os import listdir, rename |
| 15 |
from os.path import isfile, join |
| 16 |
|
| 17 |
# ouverture du fichier Excel
|
| 18 |
from xml.dom import minidom |
| 19 |
|
| 20 |
## les paramètres :
|
| 21 |
myxmlfile = sys.argv[1] #chemin relatif/nom du fichier XML |
| 22 |
mypath = sys.argv[2] #chemin système jusqu'au script |
| 23 |
|
| 24 |
print "L'encodage du système python:", sys.getdefaultencoding() ## ASCII |
| 25 |
print "L'encodage des fichiers : ", sys.getfilesystemencoding() ## UTF-8 |
| 26 |
|
| 27 |
#### NON CONSEILLE apparemment mais bon ???
|
| 28 |
reload(sys)
|
| 29 |
sys.setdefaultencoding('utf8')
|
| 30 |
|
| 31 |
inputxmlfile = join(mypath, myxmlfile); # Fichier XML d'entrée
|
| 32 |
print "InputFile XML : ",inputxmlfile |
| 33 |
resFrfile = join(mypath, 'newFr.xml') # Fichier résultat |
| 34 |
print "OutputFile XML : ", resFrfile # Fichier XML de sortie |
| 35 |
|
| 36 |
|
| 37 |
def findTextChild(node, strText): |
| 38 |
#print "\tNode [", node.nodeName, "]"
|
| 39 |
nameNode = node.nodeName |
| 40 |
if nameNode == '#text': |
| 41 |
strNode = node.nodeValue.encode('utf-8')#, 'ignore') |
| 42 |
if strText is None: |
| 43 |
strReturn = "" + strNode
|
| 44 |
else :
|
| 45 |
strReturn = str(strText) + strNode
|
| 46 |
|
| 47 |
return strReturn
|
| 48 |
elif nameNode == 'note': |
| 49 |
return strText
|
| 50 |
else :
|
| 51 |
if node.hasChildNodes():
|
| 52 |
for child in node.childNodes: |
| 53 |
strText = findTextChild(child, strText) |
| 54 |
return strText
|
| 55 |
|
| 56 |
|
| 57 |
def findText(childCell, titlecell): |
| 58 |
if childCell.hasChildNodes():
|
| 59 |
for child in childCell.childNodes: |
| 60 |
nameChildCell = child.nodeName |
| 61 |
if nameChildCell == '#text': |
| 62 |
strNode = child.nodeValue.encode('utf-8')#, 'ignore') |
| 63 |
if titlecell is None: |
| 64 |
titlecell = "" + strNode
|
| 65 |
else :
|
| 66 |
titlecell = str(titlecell) + strNode
|
| 67 |
else :
|
| 68 |
titlecell = findTextChild(child, titlecell) |
| 69 |
return titlecell
|
| 70 |
|
| 71 |
#<text name="1550_Torrentiniana">
|
| 72 |
# <body>
|
| 73 |
# <div xml:id="t1_Bo" type="Book" rend="Oeuvre">
|
| 74 |
# <seg xml:id="t1_Seg1" type="Segment" n="1" rend="Segment 1">PITTORE SCULTORE ET ARCHITETTO</seg>
|
| 75 |
|
| 76 |
#<text name="Azpilcueta_pt_1549">
|
| 77 |
# <front type="Prologue" xml:id="p1_Pr">
|
| 78 |
# <head type="Title" xml:id="p1_Pr-Seg0">PREFACE TO THE READER, Portuguese Edition, 1549</head>
|
| 79 |
# <seg n="1" type="Segment" xml:id="p1_Pr-Seg1">El doctor Martin de Azpilcueta Nauarro al lector</seg>
|
| 80 |
|
| 81 |
# xml:id="i1_Ch10-Seg12"
|
| 82 |
|
| 83 |
def buildHead(elRoot, textId, divId, textHead): |
| 84 |
headId = textId + "_" + divId+ "-Seg0" |
| 85 |
#print "#build Head ",headId
|
| 86 |
|
| 87 |
### ELEMENT <head>
|
| 88 |
strHead = u"head"
|
| 89 |
headEl = ET.SubElement(elRoot, strHead.encode('utf-8'))
|
| 90 |
|
| 91 |
### with text node
|
| 92 |
#print "## texte normal en sortie ## ",type(textHead), textSeg
|
| 93 |
headEl.text = str(textHead).encode('utf-8') |
| 94 |
|
| 95 |
### @type = "Title"
|
| 96 |
typeHead = u"Title"
|
| 97 |
headEl.set("type", typeHead.encode('utf-8')) |
| 98 |
### @xml:id = "Segment 1"
|
| 99 |
headEl.set("xml:id", headId.encode('utf-8')) |
| 100 |
return headEl
|
| 101 |
|
| 102 |
def buildDivision(elRoot, textId, numId): |
| 103 |
divId = textId + "_" + "Ch" + numId |
| 104 |
#print "#build Div ",divId
|
| 105 |
|
| 106 |
### ELEMENT <div>
|
| 107 |
strDiv = u"div"
|
| 108 |
divEl = ET.SubElement(elRoot, strDiv.encode('utf-8'))
|
| 109 |
|
| 110 |
### @n = "1"
|
| 111 |
divEl.set("n", numId.encode('utf-8')) |
| 112 |
### @type = "Chapitre"
|
| 113 |
typeDiv = u"Chapitre"
|
| 114 |
divEl.set("type", typeDiv.encode('utf-8')) |
| 115 |
### @xml:id = "Div 1"
|
| 116 |
divEl.set("xml:id", divId.encode('utf-8')) |
| 117 |
return divEl
|
| 118 |
|
| 119 |
def buildSegment(elRoot, textId, divId, textSeg, numSeg): |
| 120 |
segId = textId + "_" + divId+ "-Seg"+ numSeg |
| 121 |
#print "#build Segment ",segId
|
| 122 |
|
| 123 |
### ELEMENT <seg>
|
| 124 |
strSeg = u"seg"
|
| 125 |
segEl = ET.SubElement(elRoot, strSeg.encode('utf-8'))#, 'ignore')) |
| 126 |
|
| 127 |
### with text node
|
| 128 |
#print "## texte normal en sortie ## ",type(textSeg), textSeg
|
| 129 |
segEl.text = str(textSeg).encode('utf-8')#, 'ignore') |
| 130 |
|
| 131 |
### @n = "1"
|
| 132 |
segEl.set("n", numSeg.encode('utf-8'))#, 'ignore')) |
| 133 |
### @type = "Segment"
|
| 134 |
typeSeg = u"Segment"
|
| 135 |
segEl.set("type", typeSeg.encode('utf-8'))#, 'ignore')) |
| 136 |
### @xml:id = "Segment 1"
|
| 137 |
segEl.set("xml:id", segId.encode('utf-8'))#, 'ignore')) |
| 138 |
return segEl
|
| 139 |
|
| 140 |
|
| 141 |
def buildMetadataCorpus(elRoot): |
| 142 |
headerEl = ET.SubElement(elRoot, 'teiHeader')
|
| 143 |
fileDescEl = ET.SubElement(headerEl, 'fileDesc')
|
| 144 |
|
| 145 |
#### <titleStmt>
|
| 146 |
editionStmtEl = ET.SubElement(fileDescEl, 'editionStmt')
|
| 147 |
pEl = ET.SubElement(editionStmtEl, 'p')
|
| 148 |
pEl.text = 'à donner des détails'
|
| 149 |
|
| 150 |
#### <extent>
|
| 151 |
extentEl = ET.SubElement(fileDescEl, 'extent')
|
| 152 |
pEl = ET.SubElement(extentEl, 'p')
|
| 153 |
pEl.text = '?? segments alignés, ?? mots'
|
| 154 |
|
| 155 |
#### <publicationStmt>
|
| 156 |
publicationStmtEl = ET.SubElement(fileDescEl, 'publicationStmt')
|
| 157 |
dateEl = ET.SubElement(publicationStmtEl, 'date')
|
| 158 |
dateEl.text = '2017'
|
| 159 |
pubPlaceEl = ET.SubElement(publicationStmtEl, 'pubPlace')
|
| 160 |
pubPlaceEl.text = 'Tours'
|
| 161 |
publisherEl = ET.SubElement(publicationStmtEl, 'publisher')
|
| 162 |
publisherEl.text = 'Centre de Renaissance de Tours'
|
| 163 |
|
| 164 |
#### <sourceDesc>
|
| 165 |
sourceDescEl = ET.SubElement(fileDescEl, 'sourceDesc')
|
| 166 |
biblStructEl = ET.SubElement(sourceDescEl, 'biblStructEl')
|
| 167 |
monogrEl = ET.SubElement(biblStructEl, 'monogr')
|
| 168 |
|
| 169 |
authorEl = ET.SubElement(monogrEl, 'author')
|
| 170 |
authorEl.text = 'Toshinori Uetano'
|
| 171 |
titleEl = ET.SubElement(monogrEl, 'title')
|
| 172 |
titleEl.text = 'Corpus parallèle de Arcardia, de Jacopo Sannazaro'
|
| 173 |
respStmtEl = ET.SubElement(monogrEl, 'respStmt')
|
| 174 |
respEl = ET.SubElement(respStmtEl, 'resp')
|
| 175 |
respEl.text = '??'
|
| 176 |
nameEl = ET.SubElement(respStmtEl, 'name')
|
| 177 |
nameEl.text = '??'
|
| 178 |
imprintEl = ET.SubElement(monogrEl, 'imprint')
|
| 179 |
publisherEl = ET.SubElement(imprintEl, 'publisher')
|
| 180 |
publisherEl.text = "???"
|
| 181 |
dateEl = ET.SubElement(imprintEl, 'date')
|
| 182 |
dateEl.text = "2017"
|
| 183 |
|
| 184 |
#### <encodingDesc>
|
| 185 |
encodingDescEl = ET.SubElement(headerEl, 'encodingDesc')
|
| 186 |
projectDescEl = ET.SubElement(encodingDescEl, 'projectDesc')
|
| 187 |
pEl = ET.SubElement(projectDescEl, 'p')
|
| 188 |
pEl.text = 'Le corpus est le résultat d\'une compilation de textes etc...'
|
| 189 |
|
| 190 |
editorialDeclEl = ET.SubElement(encodingDescEl, 'editorialDecl')
|
| 191 |
correctionEl = ET.SubElement(editorialDeclEl, 'correction')
|
| 192 |
pEl = ET.SubElement(correctionEl, 'p')
|
| 193 |
pEl.text = 'Le travail éditorial consiste à ...'
|
| 194 |
|
| 195 |
segmentationEl = ET.SubElement(editorialDeclEl, 'segmentation')
|
| 196 |
pEl = ET.SubElement(segmentationEl, 'p')
|
| 197 |
pEl.text = 'La division du texte en segments philologiques correspond à ...'
|
| 198 |
|
| 199 |
|
| 200 |
def buildMetadata(elRoot, type): |
| 201 |
headerEl = ET.SubElement(elRoot, 'teiHeader')
|
| 202 |
fileDescEl = ET.SubElement(headerEl, 'fileDesc')
|
| 203 |
|
| 204 |
#### <titleStmt>
|
| 205 |
titleStmtEl = ET.SubElement(fileDescEl, 'titleStmt')
|
| 206 |
titleEl = ET.SubElement(titleStmtEl, 'title')
|
| 207 |
titleEl.text = '????'
|
| 208 |
|
| 209 |
#### <extent>
|
| 210 |
extentEl = ET.SubElement(fileDescEl, 'extent')
|
| 211 |
extentEl.text = 'Taille ....'
|
| 212 |
|
| 213 |
#### <publicationStmt>
|
| 214 |
publicationStmtEl = ET.SubElement(fileDescEl, 'publicationStmt')
|
| 215 |
dateEl = ET.SubElement(publicationStmtEl, 'date')
|
| 216 |
#date.text = 'Taille ....'
|
| 217 |
publisherEl = ET.SubElement(publicationStmtEl, 'publisher')
|
| 218 |
#publisherEl.text = 'Taille ....'
|
| 219 |
addressEl = ET.SubElement(publicationStmtEl, 'address')
|
| 220 |
#addressEl.text = 'Taille ....'
|
| 221 |
|
| 222 |
#### <sourceDesc>
|
| 223 |
sourceDescEl = ET.SubElement(fileDescEl, 'sourceDesc')
|
| 224 |
biblStructEl = ET.SubElement(sourceDescEl, 'biblStructEl')
|
| 225 |
monogrEl = ET.SubElement(biblStructEl, 'monogr')
|
| 226 |
|
| 227 |
if type == 'it': |
| 228 |
monogrEl.set("ana", "16e") |
| 229 |
monogrEl.set("lang", "it") |
| 230 |
monogrEl.set("xml:lang", "it") |
| 231 |
monogrEl.set("xml:id", "it1") |
| 232 |
titleEl = ET.SubElement(monogrEl, 'title')
|
| 233 |
titleEl.text = 'Arcadia'
|
| 234 |
authorEl = ET.SubElement(monogrEl, 'author')
|
| 235 |
authorEl.text = 'Francesco Erspamer'
|
| 236 |
authorEl.set("xml:lang", "it") |
| 237 |
editorEl = ET.SubElement(monogrEl, 'editor')
|
| 238 |
editorEl.text = 'Alde ??'
|
| 239 |
imprintEl = ET.SubElement(monogrEl, 'imprint')
|
| 240 |
publisherEl = ET.SubElement(imprintEl, 'publisher')
|
| 241 |
publisherEl.text = "édition de Venise, Alde ?"
|
| 242 |
dateEl = ET.SubElement(imprintEl, 'date')
|
| 243 |
dateEl.text = "1505"
|
| 244 |
|
| 245 |
elif type == 'fr': |
| 246 |
monogrEl.set("ana", "16e") |
| 247 |
monogrEl.set("lang", "fr") |
| 248 |
monogrEl.set("xml:lang", "fr") |
| 249 |
monogrEl.set("xml:id", "fr1") |
| 250 |
titleEl = ET.SubElement(monogrEl, 'title')
|
| 251 |
titleEl.text = 'Arcadie'
|
| 252 |
authorEl = ET.SubElement(monogrEl, 'author')
|
| 253 |
authorEl.text = 'Jehan Martin'
|
| 254 |
authorEl.set("xml:lang", "fr") |
| 255 |
editorEl = ET.SubElement(monogrEl, 'editor')
|
| 256 |
editorEl.text = 'De Vascosan et Corrozet ?'
|
| 257 |
imprintEl = ET.SubElement(monogrEl, 'imprint')
|
| 258 |
publisherEl = ET.SubElement(imprintEl, 'publisher')
|
| 259 |
publisherEl.text = "édition de Michel de Vascosan pour luy et Gilles Corrozet ?"
|
| 260 |
dateEl = ET.SubElement(imprintEl, 'date')
|
| 261 |
dateEl.text = "1544"
|
| 262 |
|
| 263 |
else:
|
| 264 |
print "NO OTHER TEXT normally ?" |
| 265 |
|
| 266 |
#### <encodingDesc>
|
| 267 |
encodingDescEl = ET.SubElement(headerEl, 'encodingDesc')
|
| 268 |
editorialDeclEl = ET.SubElement(encodingDescEl, 'editorialDecl')
|
| 269 |
normalizationEl = ET.SubElement(editorialDeclEl, 'normalization')
|
| 270 |
|
| 271 |
profileDescEl = ET.SubElement(headerEl, 'profileDesc')
|
| 272 |
langUsageEl = ET.SubElement(profileDescEl, 'langUsage')
|
| 273 |
languageEl = ET.SubElement(langUsageEl, 'language')
|
| 274 |
languageEl.set("ident", type) |
| 275 |
|
| 276 |
|
| 277 |
|
| 278 |
def buildText(elRoot, type): |
| 279 |
textEl = ET.SubElement(elRoot, 'text')
|
| 280 |
if type== 'it': |
| 281 |
textEl.set("name", "Erspamer_1505") |
| 282 |
elif type == 'fr': |
| 283 |
textEl.set("name", "Martin_1544") |
| 284 |
else:
|
| 285 |
print "No attribute NAME here !!!!" |
| 286 |
bodyEl = ET.SubElement(textEl, 'body')
|
| 287 |
#if type == 'it':
|
| 288 |
#elif type == 'fr':
|
| 289 |
return bodyEl
|
| 290 |
|
| 291 |
|
| 292 |
def findTitleSeg(title): |
| 293 |
titleFull = ''
|
| 294 |
if title :
|
| 295 |
if ',' in title : |
| 296 |
titleTable = title.split(',')
|
| 297 |
if len(titleTable) >= 2: |
| 298 |
### in LEFT PART any space will be replaced by "_"
|
| 299 |
titlecellLeft = titleTable[0]
|
| 300 |
titlecellLeft = titlecellLeft.replace(' ','_') |
| 301 |
|
| 302 |
### in RIGHT PART, some mistakes in the string
|
| 303 |
titlecellRight = ""
|
| 304 |
cellRight = titleTable[1]
|
| 305 |
if "-" in cellRight : |
| 306 |
cellRightTable = cellRight.split('-')
|
| 307 |
numC = 0
|
| 308 |
for c in cellRightTable: |
| 309 |
right = re.sub('[^0-9]*', '', c) |
| 310 |
if numC == 1: |
| 311 |
titlecellRight = titlecellRight + '-' + right
|
| 312 |
else :
|
| 313 |
titlecellRight = titlecellRight + right |
| 314 |
numC = numC + 1
|
| 315 |
|
| 316 |
else :
|
| 317 |
titlecellRight = re.sub('[^0-9]*', '', cellRight) |
| 318 |
|
| 319 |
titleFull = titlecellLeft+"_"+titlecellRight
|
| 320 |
#print "TITLE FULL : ",titleFull
|
| 321 |
|
| 322 |
else :
|
| 323 |
print "ATTTTTTTTTTENTION !!! ", len(titleCellTable) |
| 324 |
titleFull = title |
| 325 |
else :
|
| 326 |
if "-" in title : |
| 327 |
titleTable = title.split('-')
|
| 328 |
numC = 0
|
| 329 |
for c in titleTable: |
| 330 |
titleStr = re.sub('[^0-9]*', '', c) |
| 331 |
if numC == 1: |
| 332 |
titleFull = titleFull + '-' + titleStr
|
| 333 |
else :
|
| 334 |
titleFull = titleFull + titleStr |
| 335 |
numC = numC + 1
|
| 336 |
|
| 337 |
else :
|
| 338 |
titleFull = title.replace(' ','_') |
| 339 |
#titleFull = re.sub('[^0-9]*', '', title)
|
| 340 |
#print "TITLE FULL : ",titleFull
|
| 341 |
return titleFull
|
| 342 |
|
| 343 |
###### Preparing the bitext TEI output file #######
|
| 344 |
elRootCorpus = ET.Element("TeiCorpus")
|
| 345 |
buildMetadataCorpus(elRootCorpus) |
| 346 |
|
| 347 |
#### IT ####
|
| 348 |
textIdIt = "it1"
|
| 349 |
elRootIt = ET.SubElement(elRootCorpus, "TEI")
|
| 350 |
buildMetadata(elRootIt, "it")
|
| 351 |
elTextIt = buildText(elRootIt, "it")
|
| 352 |
|
| 353 |
#### FR ####
|
| 354 |
textIdFr = "fr1"
|
| 355 |
elRootFr = ET.SubElement(elRootCorpus, "TEI")
|
| 356 |
buildMetadata(elRootFr, "fr")
|
| 357 |
elTextFr = buildText(elRootFr, "fr")
|
| 358 |
|
| 359 |
|
| 360 |
##############################
|
| 361 |
# PARSING du fichier XML #
|
| 362 |
# mapping entre les titres #
|
| 363 |
# et ajout de l'id dans XML #
|
| 364 |
##############################
|
| 365 |
|
| 366 |
#<row>
|
| 367 |
# <cell>Ecloga II, vv. 1-12</cell>
|
| 368 |
# <cell>
|
| 369 |
# <p rend="justify">
|
| 370 |
# <hi rend="italic">Itene</hi>
|
| 371 |
# <hi rend="italic">
|
| 372 |
# <note xml:id="ftn121" place="foot" n="121"> <hi rend="italic">itene</hi> : andatevene. Cfr. Conti, <hi rend="italic">Canzoniere</hi>, CXLIX, 7-8 : “Itene a casa, et noi lassate al bosco / pasciute pecorelle” (Erspamer).</note>
|
| 373 |
# </hi>
|
| 374 |
# <hi rend="italic"> all'ombra degli </hi>
|
| 375 |
# <hi rend="color(#ff0000)italic">ameni faggi</hi>
|
| 376 |
# <hi rend="italic">,</hi></p>
|
| 377 |
# <p rend="justify italic">pasciute pecorelle, omai che 'l sole</p>
|
| 378 |
# <p rend="justify italic">sul mezzo giorno indrizza i caldi raggi.</p>
|
| 379 |
# <p rend="justify">
|
| 380 |
# <hi rend="italic">Ivi udirete </hi>
|
| 381 |
# <hi rend="bold italic">l'alte</hi>
|
| 382 |
# <hi rend="italic">
|
| 383 |
# <note xml:id="ftn122" place="foot" n="122"> <hi rend="italic">alte</hi> : pronunciate a voce alta (piú che 'nobili' : lo stile pastorale è infatti umile per definizione ; cfr. P, 4 ; IIIe, 29 ; X, 19) (Erspamer).</note>
|
| 384 |
# </hi>
|
| 385 |
# <hi rend="bold italic"> mie parole</hi>
|
| 386 |
# </p>
|
| 387 |
|
| 388 |
|
| 389 |
#### READING the XML TEI file #####
|
| 390 |
doc = minidom.parse(inputxmlfile) |
| 391 |
root = doc.documentElement |
| 392 |
|
| 393 |
numTable = 1
|
| 394 |
for table in root.getElementsByTagName('table'): |
| 395 |
divId = "Ch" + str(numTable) |
| 396 |
elDivIt = buildDivision(elTextIt, textIdIt, str(numTable))
|
| 397 |
elDivFr = buildDivision(elTextFr, textIdFr, str(numTable))
|
| 398 |
if table.hasChildNodes():
|
| 399 |
#print "\tchild"
|
| 400 |
numRow = 1
|
| 401 |
for childRow in table.childNodes: |
| 402 |
name = childRow.nodeName |
| 403 |
#print name
|
| 404 |
if name == 'row': |
| 405 |
#print "in row real"
|
| 406 |
if childRow.hasChildNodes():
|
| 407 |
numCell = 0
|
| 408 |
titlecell = u""
|
| 409 |
for childCell in childRow.childNodes: |
| 410 |
nameCell = childCell.nodeName |
| 411 |
if childCell.nodeName == 'cell': |
| 412 |
cell = u""
|
| 413 |
textfr = u""
|
| 414 |
textit = u""
|
| 415 |
#print "==========Cell=========="
|
| 416 |
if numCell == 0 : |
| 417 |
titlecell = findText(childCell, titlecell) |
| 418 |
titleorigin = titlecell |
| 419 |
## Exemple : A la Sampogna, 17-18íòú
|
| 420 |
titlecell = findTitleSeg(titlecell) |
| 421 |
print "TITRE ; ",titleorigin, ";", titlecell |
| 422 |
|
| 423 |
if titlecell:
|
| 424 |
buildHead(elDivIt, textIdIt, divId, titlecell) |
| 425 |
buildHead(elDivFr, textIdFr, divId, titlecell) |
| 426 |
elif numCell == 1 : ### FR |
| 427 |
textit = findText(childCell, textit) |
| 428 |
#print "[it] : ",textit
|
| 429 |
buildSegment(elDivIt, textIdIt, divId, textit, str(numRow))
|
| 430 |
|
| 431 |
elif numCell == 2 : ### IT |
| 432 |
textfr = findText(childCell, textfr) |
| 433 |
#print "[fr] : ",textfr
|
| 434 |
buildSegment(elDivFr, textIdFr, divId, textfr, str(numRow))
|
| 435 |
|
| 436 |
else : ### |
| 437 |
print "[what cell] ???????????" |
| 438 |
if childCell.hasChildNodes():
|
| 439 |
|
| 440 |
for child in childCell.childNodes: |
| 441 |
nameChildCell = child.nodeName |
| 442 |
#print nameChildCell
|
| 443 |
if nameChildCell == '#text': |
| 444 |
cell = child.nodeValue |
| 445 |
else :
|
| 446 |
cell = findTextChild(child, "")
|
| 447 |
print "OTHER ? ", cell |
| 448 |
numCell = numCell + 1
|
| 449 |
#print "[N]", numCell
|
| 450 |
numRow = numRow + 1
|
| 451 |
print "Chapitre ",numTable |
| 452 |
numTable = numTable + 1
|
| 453 |
|
| 454 |
treeFr = ET.ElementTree(elRootCorpus) |
| 455 |
#treeFr.write(sys.stdout)
|
| 456 |
resFrfile.encode("utf-8")
|
| 457 |
treeFr.write(resFrfile) |
| 458 |
#ET.tostring(treeFr, encoding='utf-8', method="xml")
|