258
259
260
261
262
263
264
265
266
267
268
269
270
271
|
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
|
+
+
|
sText = sText.replace(" ", ' ') # nbsp
if " " in sText:
sText = sText.replace(" ", ' ') # nnbsp
if "'" in sText:
sText = sText.replace("'", "’")
if "‑" in sText:
sText = sText.replace("‑", "-") # nobreakdash
if "@@" in sText:
sText = re.sub("@@+", "", sText)
# parse sentences
for iStart, iEnd in _getSentenceBoundaries(sText):
if 4 < (iEnd - iStart) < 2000:
try:
self.sSentence = sText[iStart:iEnd]
self.sSentence0 = self.sText0[iStart:iEnd]
|
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
|
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
|
-
+
+
+
|
def rewriteText (self, sText, sRepl, iGroup, m, bUppercase):
"text processor: write <sRepl> in <sText> at <iGroup> position"
nLen = m.end(iGroup) - m.start(iGroup)
if sRepl == "*":
sNew = " " * nLen
elif sRepl == "_":
sNew = sRepl + " " * (nLen-1)
sNew = "_" * nLen
elif sRepl == "@":
sNew = "@" * nLen
elif sRepl[0:1] == "=":
sNew = globals()[sRepl[1:]](sText, m)
sNew = sNew + " " * (nLen-len(sNew))
if bUppercase and m.group(iGroup)[0:1].isupper():
sNew = sNew.capitalize()
else:
sNew = m.expand(sRepl)
|