51
52
53
54
55
56
57
58
59
60
61
62
63
64
|
sCode = re.sub('(look_chk1\\(dDA, sx?[][.a-z:()]*, [0-9a-z.()]+), "([^"]+)"', "\\1, /\\2/i", sCode)
sCode = re.sub('m\\.group\\((\\d+)\\) +in +(a[a-zA-Z]+)', "\\2.has(m[\\1])", sCode)
sCode = sCode.replace("(?<!-)", "") # todo
# slices
sCode = sCode.replace("[:m.start()]", ".slice(0,m.index)")
sCode = sCode.replace("[m.end():]", ".slice(m.end[0])")
sCode = sCode.replace("[m.start():m.end()]", ".slice(m.index, m.end[0])")
sCode = re.sub("\\[(-?\\d+):(-?\\d+)\\]", ".slice(\\1,\\2)", sCode)
sCode = re.sub("\\[(-?\\d+):\\]", ".slice(\\1)", sCode)
sCode = re.sub("\\[:(-?\\d+)\\]", ".slice(0,\\1)", sCode)
# regex matches
sCode = sCode.replace(".end()", ".end[0]")
sCode = sCode.replace(".start()", ".index")
sCode = sCode.replace("m.group()", "m[0]")
|
>
>
|
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
sCode = re.sub('(look_chk1\\(dDA, sx?[][.a-z:()]*, [0-9a-z.()]+), "([^"]+)"', "\\1, /\\2/i", sCode)
sCode = re.sub('m\\.group\\((\\d+)\\) +in +(a[a-zA-Z]+)', "\\2.has(m[\\1])", sCode)
sCode = sCode.replace("(?<!-)", "") # todo
# slices
sCode = sCode.replace("[:m.start()]", ".slice(0,m.index)")
sCode = sCode.replace("[m.end():]", ".slice(m.end[0])")
sCode = sCode.replace("[m.start():m.end()]", ".slice(m.index, m.end[0])")
sCode = sCode.replace('[lToken[nLastToken]["nEnd"]:]', '.slice(lToken[nLastToken]["nEnd"])')
sCode = sCode.replace('[:lToken[1+nTokenOffset]["nStart"]]', '.slice(0,lToken[1+nTokenOffset]["nStart"])')
sCode = re.sub("\\[(-?\\d+):(-?\\d+)\\]", ".slice(\\1,\\2)", sCode)
sCode = re.sub("\\[(-?\\d+):\\]", ".slice(\\1)", sCode)
sCode = re.sub("\\[:(-?\\d+)\\]", ".slice(0,\\1)", sCode)
# regex matches
sCode = sCode.replace(".end()", ".end[0]")
sCode = sCode.replace(".start()", ".index")
sCode = sCode.replace("m.group()", "m[0]")
|
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
|
sRegex = sRegex + "i"
if not lNegLookBeforeRegex:
lNegLookBeforeRegex = None
return (sRegex, lNegLookBeforeRegex)
def pyRuleToJS (lRule, dJSREGEXES, sWORDLIMITLEFT):
lRuleJS = copy.deepcopy(lRule)
del lRule[-1] # tGroups positioning codes are useless for Python
# error messages
for aAction in lRuleJS[6]:
if aAction[1] == "-":
aAction[2] = aAction[2].replace(" ", " ") # nbsp --> nnbsp
aAction[4] = aAction[4].replace("« ", "« ").replace(" »", " »").replace(" :", " :").replace(" :", " :")
# js regexes
lRuleJS[1], lNegLookBehindRegex = regex2js(dJSREGEXES.get(lRuleJS[3], lRuleJS[1]), sWORDLIMITLEFT)
lRuleJS.append(lNegLookBehindRegex)
return lRuleJS
def writeRulesToJSArray (lRules):
sArray = "[\n"
for sOption, aRuleGroup in lRules:
sArray += ' ["' + sOption + '", [\n' if sOption else " [false, [\n"
for sRegex, bCaseInsensitive, sLineId, sRuleId, nPriority, lActions, aGroups, aNegLookBehindRegex in aRuleGroup:
sArray += ' [' + sRegex + ", "
sArray += "true, " if bCaseInsensitive else "false, "
sArray += '"' + sLineId + '", '
sArray += '"' + sRuleId + '", '
sArray += str(nPriority) + ", "
sArray += json.dumps(lActions, ensure_ascii=False) + ", "
sArray += json.dumps(aGroups, ensure_ascii=False) + ", "
sArray += json.dumps(aNegLookBehindRegex, ensure_ascii=False) + "],\n"
sArray += " ]],\n"
sArray += "]"
return sArray
def groupsPositioningCodeToList (sGroupsPositioningCode):
if not sGroupsPositioningCode:
return None
return [ int(sCode) if sCode.isdigit() or (sCode[0:1] == "-" and sCode[1:].isdigit()) else sCode \
for sCode in sGroupsPositioningCode.split(",") ]
|
>
>
>
>
>
>
|
|
|
|
|
|
|
|
|
|
|
>
>
>
>
>
>
|
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
|
sRegex = sRegex + "i"
if not lNegLookBeforeRegex:
lNegLookBeforeRegex = None
return (sRegex, lNegLookBeforeRegex)
def pyRuleToJS (lRule, dJSREGEXES, sWORDLIMITLEFT):
"modify Python rules -> JS rules"
lRuleJS = copy.deepcopy(lRule)
# graph rules
if lRuleJS[0] == "@@@@":
return lRuleJS
del lRule[-1] # tGroups positioning codes are useless for Python
# error messages
for aAction in lRuleJS[6]:
if aAction[1] == "-":
aAction[2] = aAction[2].replace(" ", " ") # nbsp --> nnbsp
aAction[4] = aAction[4].replace("« ", "« ").replace(" »", " »").replace(" :", " :").replace(" :", " :")
# js regexes
lRuleJS[1], lNegLookBehindRegex = regex2js(dJSREGEXES.get(lRuleJS[3], lRuleJS[1]), sWORDLIMITLEFT)
lRuleJS.append(lNegLookBehindRegex)
return lRuleJS
def writeRulesToJSArray (lRules):
"create rules as a string of arrays (to be bundled in a JSON string)"
sArray = "[\n"
for sOption, aRuleGroup in lRules:
if sOption != "@@@@":
sArray += ' ["' + sOption + '", [\n' if sOption else " [false, [\n"
for sRegex, bCaseInsensitive, sLineId, sRuleId, nPriority, lActions, aGroups, aNegLookBehindRegex in aRuleGroup:
sArray += ' [' + sRegex + ", "
sArray += "true, " if bCaseInsensitive else "false, "
sArray += '"' + sLineId + '", '
sArray += '"' + sRuleId + '", '
sArray += str(nPriority) + ", "
sArray += json.dumps(lActions, ensure_ascii=False) + ", "
sArray += json.dumps(aGroups, ensure_ascii=False) + ", "
sArray += json.dumps(aNegLookBehindRegex, ensure_ascii=False) + "],\n"
sArray += " ]],\n"
else:
sArray += ' ["' + sOption + '", [\n'
for sGraphName, sLineId in aRuleGroup:
sArray += ' ["' + sGraphName + '", "' + sLineId + '"],\n'
sArray += " ]],\n"
sArray += "]"
return sArray
def groupsPositioningCodeToList (sGroupsPositioningCode):
"convert <sGroupsPositioningCode> to a list of codes (numbers or strings)"
if not sGroupsPositioningCode:
return None
return [ int(sCode) if sCode.isdigit() or (sCode[0:1] == "-" and sCode[1:].isdigit()) else sCode \
for sCode in sGroupsPositioningCode.split(",") ]
|