10
11
12
13
14
15
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
47
48
|
import darg
dACTIONS = {}
dFUNCTIONS = {}
def prepareFunction (s, bTokenValue=False):
"convert simple rule syntax to a string of Python code"
s = s.replace("__also__", "bCondMemo")
s = s.replace("__else__", "not bCondMemo")
s = re.sub(r"(morph|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"(switchGender|has(?:(?:Mas|Fem)Form)|Simil)[(]\\(\d+)", '\\1(lToken[\\2+nTokenOffset]["sValue"]', 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"[\\](\d+)\.is(upper|lower|title)\(\)", 'lToken[\\1+nTokenOffset]["sValue"].is\\2()', s)
s = re.sub(r"[\\](\d+)\.(startswith|endswith)\(", 'lToken[\\1+nTokenOffset]["sValue"].\\2(', s)
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)
if bTokenValue:
# token values are used as parameter
s = re.sub(r"[\\](\d+)", 'lToken[\\1+nTokenOffset]["sValue"]', s)
else:
# tokens used as parameter
s = re.sub(r"[\\](\d+)", 'lToken[\\1+nTokenOffset]', s)
return s
def genTokenLines (sTokenLine, dDef):
"tokenize a string and return a list of lines of tokens"
lToken = sTokenLine.split()
lTokenLines = None
|
|
|
|
|
<
<
|
<
<
<
|
10
11
12
13
14
15
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
|
import darg
dACTIONS = {}
dFUNCTIONS = {}
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 = re.sub(r"(morph|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"(switchGender|has(?:(?:Mas|Fem)Form)|Simil)[(]\\(\d+)", '\\1(lToken[\\2+nTokenOffset]["sValue"]', 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"[\\](\d+)\.is(upper|lower|title)\(\)", 'lToken[\\1+nTokenOffset]["sValue"].is\\2()', s)
#s = re.sub(r"[\\](\d+)\.(startswith|endswith)\(", 'lToken[\\1+nTokenOffset]["sValue"].\\2(', s)
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
|
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
|
sURL = ""
mURL = re.search("[|] *(https?://.*)", sMsg)
if mURL:
sURL = mURL.group(1).strip()
sMsg = sMsg[:mURL.start(0)].strip()
checkTokenNumbers(sMsg, sActionId, nToken)
if sMsg[0:1] == "=":
sMsg = prepareFunction(sMsg[1:], True)
dFUNCTIONS["g_m_"+sActionId] = sMsg
sMsg = "=g_m_"+sActionId
else:
checkIfThereIsCode(sMsg, sActionId)
# checking consistancy
checkTokenNumbers(sAction, sActionId, nToken)
|
|
|
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
|
sURL = ""
mURL = re.search("[|] *(https?://.*)", sMsg)
if mURL:
sURL = mURL.group(1).strip()
sMsg = sMsg[:mURL.start(0)].strip()
checkTokenNumbers(sMsg, sActionId, nToken)
if sMsg[0:1] == "=":
sMsg = prepareFunction(sMsg[1:])
dFUNCTIONS["g_m_"+sActionId] = sMsg
sMsg = "=g_m_"+sActionId
else:
checkIfThereIsCode(sMsg, sActionId)
# checking consistancy
checkTokenNumbers(sAction, sActionId, nToken)
|
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
|
if sAction[0:1] != "=" and cAction != "=":
checkIfThereIsCode(sAction, sActionId)
if cAction == "-":
## error detected --> suggestion
if sAction[0:1] == "=":
sAction = prepareFunction(sAction, True)
dFUNCTIONS["_g_s_"+sActionId] = sAction[1:]
sAction = "=_g_s_"+sActionId
elif sAction.startswith('"') and sAction.endswith('"'):
sAction = sAction[1:-1]
if not sMsg:
print("# Error in action at line " + sActionId + ": The message is empty.")
return [sOption, sCondition, cAction, sAction, iStartAction, iEndAction, nPriority, sMsg, sURL]
elif cAction == "~":
## text processor
if sAction[0:1] == "=":
sAction = prepareFunction(sAction, True)
dFUNCTIONS["_g_p_"+sActionId] = sAction[1:]
sAction = "=_g_p_"+sActionId
elif sAction.startswith('"') and sAction.endswith('"'):
sAction = sAction[1:-1]
return [sOption, sCondition, cAction, sAction, iStartAction, iEndAction]
elif cAction == "/":
## tags
|
|
|
|
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
|
if sAction[0:1] != "=" and cAction != "=":
checkIfThereIsCode(sAction, sActionId)
if cAction == "-":
## error detected --> suggestion
if sAction[0:1] == "=":
sAction = prepareFunction(sAction)
dFUNCTIONS["_g_s_"+sActionId] = sAction[1:]
sAction = "=_g_s_"+sActionId
elif sAction.startswith('"') and sAction.endswith('"'):
sAction = sAction[1:-1]
if not sMsg:
print("# Error in action at line " + sActionId + ": The message is empty.")
return [sOption, sCondition, cAction, sAction, iStartAction, iEndAction, nPriority, sMsg, sURL]
elif cAction == "~":
## text processor
if sAction[0:1] == "=":
sAction = prepareFunction(sAction)
dFUNCTIONS["_g_p_"+sActionId] = sAction[1:]
sAction = "=_g_p_"+sActionId
elif sAction.startswith('"') and sAction.endswith('"'):
sAction = sAction[1:-1]
return [sOption, sCondition, cAction, sAction, iStartAction, iEndAction]
elif cAction == "/":
## tags
|