def save_file(self, filePath):
docF = DocReader(filePath)
rawCont = docF.read()
rawCont = rawCont.decode(CODING)
self.readChars = 0
size = len(rawCont)
contentParted = rawCont.partition(NEW_LINE)
caption = contentParted[0]
content = contentParted[2]
paraSplitter = '%s\x0c' %(NEW_LINE)
paragraphs = content.split(paraSplitter)
# print filePath, "got %d paragraphs" %(len(paragraphs))
FILE_ID = self.dbi.addFile(path.basename(filePath), caption)
for para in paragraphs:
paraCaption, __, paraContent = para.partition(NEW_LINE)
self.readChars += len(para) + len(paraSplitter)
PARAGRAPH_ID = self.dbi.addParagraph(paraCaption, FILE_ID)
curRdNr = None
rdNrContent = []
for line in paraContent.split(NEW_LINE):
# eigentlich werden randnummern in textboxes als eigene Zeile erkannt...
if line.isdigit():
if curRdNr != None:
RDNR_ID = self.dbi.addRdNr(curRdNr, PARAGRAPH_ID)
self.save_content(rdNrContent, RDNR_ID, PARAGRAPH_ID, FILE_ID)
rdNrContent = []
curRdNr = int(line)
# self.readChars += len(line) + len(NEW_LINE)
# ... wenn man aber die Dokumente aus odt importiert, werden die in die zeile vorne drangehangen(zusammen mit 2 tabs)
elif re.match("\d+\t\t", line[:10]):
partition = line.partition("\t\t")
if curRdNr != None:
RDNR_ID = self.dbi.addRdNr(curRdNr, PARAGRAPH_ID)
self.save_content(rdNrContent, RDNR_ID, PARAGRAPH_ID, FILE_ID)
rdNrContent = [partition[2].strip()]
curRdNr = int(partition[0])
else:
rdNrContent.append(line)
self.fileStatusUpdated.emit(self.readChars, size)
def readDocFile(fName):
docF = DocReader(fName)
rawCont = docF.read().decode("latin-1").encode("utf-8")
contentParted = rawCont.partition(NEW_LINE)
caption = contentParted[0]
content = contentParted[2]
# createDirIfNeeded(path.join(PLAIN_FOLDER, caption))
paragraphs = content.split(u"%s\x0c" % (NEW_LINE))
cRESULT = {}
# nRESULT = {}
for rawPara in paragraphs:
para = Paragraph(rawPara, caption)
for k in para.rdWordMap:
for w in para.rdWordMap[k].capWords.values():
cRESULT = addWord(cRESULT, w)
# for w in para.rdWordMap[k].normalWords.values():
# nRESULT = addWord(nRESULT, w)
return cRESULT
# Miette is "small sweet thing" in french
from cfb.reader import CfbReader
from doc.reader import DocReader
from tools import hex_dump
r = DocReader('../tests/doc/mw_lorem_ipsum.doc')
#r = DocReader('../tests/doc/gd_lorem_ipsum.doc')
#r = DocReader('../tests/doc/oo_lorem_ipsum.doc')
#r = DocReader('../tests/doc/te_lorem_ipsum.doc')
#r = DocReader('../tests/doc/mw_vesna_yandex_ru.doc')
#r = DocReader('../tests/doc/gd_vesna_yandex_ru.doc')
#r = DocReader('../tests/doc/oo_vesna_yandex_ru.doc')
#r = DocReader('../tests/doc/te_vesna_yandex_ru.doc')
print r.read()
# Miette is "small sweet thing" in french
from cfb.reader import CfbReader
from doc.reader import DocReader
from tools import hex_dump
# r = DocReader('../tests/doc/mw_lorem_ipsum.doc')
r = DocReader('../tests/doc/P_089-104.doc')
#r = DocReader('../tests/doc/gd_lorem_ipsum.doc')
#r = DocReader('../tests/doc/oo_lorem_ipsum.doc')
#r = DocReader('../tests/doc/te_lorem_ipsum.doc')
#r = DocReader('../tests/doc/mw_vesna_yandex_ru.doc')
#r = DocReader('../tests/doc/gd_vesna_yandex_ru.doc')
#r = DocReader('../tests/doc/oo_vesna_yandex_ru.doc')
#r = DocReader('../tests/doc/te_vesna_yandex_ru.doc')
out = open("out", "w")
out.write(r.read())
out.close()
