16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
|
def prepareFunction (s):
"convert simple rule syntax to a string of Python code"
s = s.replace("__also__", "bCondMemo")
s = s.replace("__else__", "not bCondMemo")
s = s.replace("sContext", "_sAppContext")
s = re.sub(r"(morph|morphVC|analyse|value|displayInfo)[(]\\(\d+)", 'g_\\1(lToken[\\2+nTokenOffset]', s)
s = re.sub(r"(select|exclude|define|define_from)[(][\\](\d+)", 'g_\\1(lToken[\\2+nTokenOffset]', s)
s = re.sub(r"(tag_before|tag_after)[(][\\](\d+)", 'g_\\1(lToken[\\2+nTokenOffset], dTags', s)
s = re.sub(r"space_after[(][\\](\d+)", 'g_space_between_tokens(lToken[\\1+nTokenOffset], lToken[\\1+nTokenOffset+1]', s)
s = re.sub(r"analyse_with_next[(][\\](\d+)", 'g_merged_analyse(lToken[\\1+nTokenOffset], lToken[\\1+nTokenOffset+1]', s)
s = re.sub(r"(morph|analyse|value)\(>1", 'g_\\1(lToken[nLastToken+1]', s) # next token
s = re.sub(r"(morph|analyse|value)\(<1", 'g_\\1(lToken[nTokenOffset]', s) # previous token
s = re.sub(r"(morph|analyse|value)\(>(\d+)", 'g_\\1(g_token(lToken, nLastToken+\\2)', s) # next token
s = re.sub(r"(morph|analyse|value)\(<(\d+)", 'g_\\1(g_token(lToken, nTokenOffset+1-\\2)', s) # previous token
s = re.sub(r"\bspell *[(]", '_oSpellChecker.isValid(', s)
s = re.sub(r"\bbefore\(\s*", 'look(sSentence[:lToken[1+nTokenOffset]["nStart"]], ', s) # before(s)
s = re.sub(r"\bafter\(\s*", 'look(sSentence[lToken[nLastToken]["nEnd"]:], ', s) # after(s)
s = re.sub(r"\bbefore0\(\s*", 'look(sSentence0[:lToken[1+nTokenOffset]["nStart"]], ', s) # before0(s)
s = re.sub(r"\bafter0\(\s*", 'look(sSentence[lToken[nLastToken]["nEnd"]:], ', s) # after0(s)
s = re.sub(r"[\\](\d+)", 'lToken[\\1+nTokenOffset]["sValue"]', s)
return s
def genTokenLines (sTokenLine, dDef):
"tokenize a string and return a list of lines of tokens"
lToken = sTokenLine.split()
lTokenLines = None
|
>
>
>
|
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
|
def prepareFunction (s):
"convert simple rule syntax to a string of Python code"
s = s.replace("__also__", "bCondMemo")
s = s.replace("__else__", "not bCondMemo")
s = s.replace("sContext", "_sAppContext")
s = re.sub(r"(morph|morphVC|analyse|value|displayInfo)[(]\\(\d+)", 'g_\\1(lToken[\\2+nTokenOffset]', s)
s = re.sub(r"(morph|morphVC|analyse|value|displayInfo)[(]\\-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1]', s)
s = re.sub(r"(select|exclude|define|define_from)[(][\\](\d+)", 'g_\\1(lToken[\\2+nTokenOffset]', s)
s = re.sub(r"(select|exclude|define|define_from)[(][\\]-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1]', s)
s = re.sub(r"(tag_before|tag_after)[(][\\](\d+)", 'g_\\1(lToken[\\2+nTokenOffset], dTags', s)
s = re.sub(r"space_after[(][\\](\d+)", 'g_space_between_tokens(lToken[\\1+nTokenOffset], lToken[\\1+nTokenOffset+1]', s)
s = re.sub(r"analyse_with_next[(][\\](\d+)", 'g_merged_analyse(lToken[\\1+nTokenOffset], lToken[\\1+nTokenOffset+1]', s)
s = re.sub(r"(morph|analyse|value)\(>1", 'g_\\1(lToken[nLastToken+1]', s) # next token
s = re.sub(r"(morph|analyse|value)\(<1", 'g_\\1(lToken[nTokenOffset]', s) # previous token
s = re.sub(r"(morph|analyse|value)\(>(\d+)", 'g_\\1(g_token(lToken, nLastToken+\\2)', s) # next token
s = re.sub(r"(morph|analyse|value)\(<(\d+)", 'g_\\1(g_token(lToken, nTokenOffset+1-\\2)', s) # previous token
s = re.sub(r"\bspell *[(]", '_oSpellChecker.isValid(', s)
s = re.sub(r"\bbefore\(\s*", 'look(sSentence[:lToken[1+nTokenOffset]["nStart"]], ', s) # before(s)
s = re.sub(r"\bafter\(\s*", 'look(sSentence[lToken[nLastToken]["nEnd"]:], ', s) # after(s)
s = re.sub(r"\bbefore0\(\s*", 'look(sSentence0[:lToken[1+nTokenOffset]["nStart"]], ', s) # before0(s)
s = re.sub(r"\bafter0\(\s*", 'look(sSentence[lToken[nLastToken]["nEnd"]:], ', s) # after0(s)
s = re.sub(r"[\\](\d+)", 'lToken[\\1+nTokenOffset]["sValue"]', s)
s = re.sub(r"[\\]-(\d+)", 'lToken[nLastToken-\\1+1]["sValue"]', s)
return s
def genTokenLines (sTokenLine, dDef):
"tokenize a string and return a list of lines of tokens"
lToken = sTokenLine.split()
lTokenLines = None
|
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
|
m = re.match("/(\\w+)/", sAction)
if m:
sOption = m.group(1)
sAction = sAction[m.end():].strip()
if nPriority == -1:
nPriority = dOptPriority.get(sOption, 4)
# valid action?
m = re.search(r"(?P<action>[-~=/%>])(?P<start>\d+\.?|)(?P<end>:\.?\d+|)>>", sAction)
if not m:
print(" # Error. No action found at: ", sActionId)
return None
# Condition
sCondition = sAction[:m.start()].strip()
if sCondition:
sCondition = changeReferenceToken(sCondition, dPos)
|
|
|
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
|
m = re.match("/(\\w+)/", sAction)
if m:
sOption = m.group(1)
sAction = sAction[m.end():].strip()
if nPriority == -1:
nPriority = dOptPriority.get(sOption, 4)
# valid action?
m = re.search(r"(?P<action>[-~=/%>])(?P<start>-?\d+\.?|)(?P<end>:\.?-?\d+|)>>", sAction)
if not m:
print(" # Error. No action found at: ", sActionId)
return None
# Condition
sCondition = sAction[:m.start()].strip()
if sCondition:
sCondition = changeReferenceToken(sCondition, dPos)
|
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
|
#sJSCallables = "// generated code, do not edit\nconst oEvalFunc = {\n"
for sFuncName, sReturn in dFUNCTIONS.items():
if sFuncName.startswith("_g_c_"): # condition
sParams = "lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, dTags, sSentence, sSentence0"
elif sFuncName.startswith("g_m_"): # message
sParams = "lToken, nTokenOffset"
elif sFuncName.startswith("_g_s_"): # suggestion
sParams = "lToken, nTokenOffset"
elif sFuncName.startswith("_g_p_"): # preprocessor
sParams = "lToken, nTokenOffset"
elif sFuncName.startswith("_g_d_"): # disambiguator
sParams = "lToken, nTokenOffset"
else:
print("# Unknown function type in [" + sFuncName + "]")
continue
|
|
|
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
|
#sJSCallables = "// generated code, do not edit\nconst oEvalFunc = {\n"
for sFuncName, sReturn in dFUNCTIONS.items():
if sFuncName.startswith("_g_c_"): # condition
sParams = "lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, dTags, sSentence, sSentence0"
elif sFuncName.startswith("g_m_"): # message
sParams = "lToken, nTokenOffset"
elif sFuncName.startswith("_g_s_"): # suggestion
sParams = "lToken, nTokenOffset, nLastToken"
elif sFuncName.startswith("_g_p_"): # preprocessor
sParams = "lToken, nTokenOffset"
elif sFuncName.startswith("_g_d_"): # disambiguator
sParams = "lToken, nTokenOffset"
else:
print("# Unknown function type in [" + sFuncName + "]")
continue
|