47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
|
sCode = re.sub(r'.replace\("([^"]+)" ?,', ".replace(/\\1/g,", sCode)
# regex
#sCode = re.sub('re.search\\("([^"]+)", *(m.group\\(\\d\\))\\)', "(\\2.search(/\\1/) >= 0)", sCode)
#sCode = re.sub(".search\\(/\\(\\?i\\)([^/]+)/\\) >= 0\\)", ".search(/\\1/i) >= 0)", sCode)
#sCode = re.sub('(look\\(sSentence0?[][.a-z0-9:()"+-]*), "\\(\\?i\\)([^"]+)"', "\\1, /\\2/i", sCode)
#sCode = re.sub('(look\\(sSentence0?[][.a-z0-9:()"+-]*), "([^"]+)"', "\\1, /\\2/", 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]")
sCode = re.sub("\\.start\\((\\d+)\\)", ".start[\\1]", sCode)
sCode = re.sub("m\\.group\\((\\d+)\\)", "m[\\1]", sCode)
# tuples -> lists
sCode = re.sub("\\((m\\.start\\[\\d+\\], m\\[\\d+\\])\\)", "[\\1]", sCode)
# regex
sCode = sCode.replace(r"\w[\w-]+", "[a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st][a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st-]+")
sCode = sCode.replace(r"/\w/", "/[a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st]/")
sCode = sCode.replace(r"[\w-]", "[a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st-]")
sCode = sCode.replace(r"[\w,]", "[a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st,]")
|
|
<
<
|
|
|
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
|
sCode = re.sub(r'.replace\("([^"]+)" ?,', ".replace(/\\1/g,", sCode)
# regex
#sCode = re.sub('re.search\\("([^"]+)", *(m.group\\(\\d\\))\\)', "(\\2.search(/\\1/) >= 0)", sCode)
#sCode = re.sub(".search\\(/\\(\\?i\\)([^/]+)/\\) >= 0\\)", ".search(/\\1/i) >= 0)", sCode)
#sCode = re.sub('(look\\(sSentence0?[][.a-z0-9:()"+-]*), "\\(\\?i\\)([^"]+)"', "\\1, /\\2/i", sCode)
#sCode = re.sub('(look\\(sSentence0?[][.a-z0-9:()"+-]*), "([^"]+)"', "\\1, /\\2/", sCode)
sCode = re.sub('m\\.group\\((\\d+)\\) +in +(a[a-zA-Z]+)', "\\2.has(m[\\1])", sCode)
sCode = re.sub('(lToken\\S+) +in +(a[a-zA-Z]+)', "\\2.has(\\1)", sCode)
# 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]")
sCode = re.sub("\\.start\\((\\d+)\\)", ".start[\\1]", sCode)
sCode = re.sub("m\\.group\\((\\d+)\\)", "m[\\1]", sCode)
# tuples -> lists
sCode = re.sub("\\((m\\.start\\[\\d+\\], m\\[\\d+\\])\\)", "[\\1]", sCode)
# regex
sCode = sCode.replace(r"[\\w", "[a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ")
sCode = sCode.replace(r"\\w", "[a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ]")
return sCode
def regex2js (sRegex, sWORDLIMITLEFT):
"converts Python regex to JS regex and returns JS regex and list of negative lookbefore assertions"
# Latin letters: http://unicode-table.com/fr/
# 0-9 and _
|