Grammalecte  Check-in [d82e5dd021]

Overview
Comment:[build][core] function info for tokens
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | core | build
Files: files | file ages | folders
SHA3-256: d82e5dd0218f71f1d7d4967ed8c045070b8924e3134d164299ec14c434f1ebeb
User & Date: olr on 2021-01-05 15:53:17
Other Links: manifest | tags
Context
2021-01-05
16:39
[core][fr] suggMasPlur: allow self suggestion check-in: 6544c2d607 user: olr tags: trunk, fr, core
15:53
[build][core] function info for tokens check-in: d82e5dd021 user: olr tags: trunk, core, build
2021-01-04
19:28
[fx][tb] editor: fix wrong variable name check-in: 03ae204c73 user: olr tags: trunk, tb, fx
Changes
Hide Diffs Side-by-Side Diffs Ignore Whitespace Patch

Modified compile_rules_graph.py from [d4d961a0bc] to [0195f7a15c].

︙
44
45
46
47
48
49
50
51
52
53
54




55
56
57
58
59
60
61

44
45
46
47
48
49
50




51
52
53
54
55
56
57
58
59
60
61








-
-
-
-
+
+
+
+








    sCode = re.sub(r"\b(select|define|definefrom|rewrite|addmorph|setmeta)[(][\\]-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1]', sCode)
    sCode = re.sub(r"\b(tagbefore|tagafter)[(][\\](\d+)", 'g_\\1(lToken[nTokenOffset+\\2], dTags', sCode)
    sCode = re.sub(r"\b(tagbefore|tagafter)[(][\\]-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1], dTags', sCode)
    sCode = re.sub(r"\bspace[(][\\](\d+)", 'g_space(lToken[nTokenOffset+\\1], lToken[nTokenOffset+\\1+1]', sCode)
    sCode = re.sub(r"\bspace[(][\\]-(\d+)", 'g_space(lToken[nLastToken-\\1+1], lToken[nLastToken-\\1+2]', sCode)
    sCode = re.sub(r"\bmorph2[(][\\](\d+)", 'g_morph2(lToken[nTokenOffset+\\1], lToken[nTokenOffset+\\1+1]', sCode)
    sCode = re.sub(r"\bmorph2[(][\\]-(\d+)", 'g_morph2(lToken[nLastToken-\\1+1], lToken[nLastToken-\\1+2]', sCode)
    sCode = re.sub(r"\b(morph0?|tag|meta|value)\(>1", 'g_\\1(lToken[nLastToken+1]', sCode)                      # next token
    sCode = re.sub(r"\b(morph0?|tag|meta|value)\(<1", 'g_\\1(lToken[nTokenOffset]', sCode)                      # previous token
    sCode = re.sub(r"\b(morph0?|tag|meta|value)\(>(\d+)", 'g_\\1(g_token(lToken, nLastToken+\\2)', sCode)       # next token
    sCode = re.sub(r"\b(morph0?|tag|meta|value)\(<(\d+)", 'g_\\1(g_token(lToken, nTokenOffset+1-\\2)', sCode)   # previous token
    sCode = re.sub(r"\b(morph0?|tag|meta|value|info)\(>1", 'g_\\1(lToken[nLastToken+1]', sCode)                      # next token
    sCode = re.sub(r"\b(morph0?|tag|meta|value|info)\(<1", 'g_\\1(lToken[nTokenOffset]', sCode)                      # previous token
    sCode = re.sub(r"\b(morph0?|tag|meta|value|info)\(>(\d+)", 'g_\\1(g_token(lToken, nLastToken+\\2)', sCode)       # next token
    sCode = re.sub(r"\b(morph0?|tag|meta|value|info)\(<(\d+)", 'g_\\1(g_token(lToken, nTokenOffset+1-\\2)', sCode)   # previous token
    sCode = re.sub(r"\bspace[(](>1)", 'g_space(lToken[nLastToken+1], g_token(lToken, nLastToken+2)', sCode)     # next token
    sCode = re.sub(r"\bspace[(](<1)", 'g_space(lToken[nTokenOffset], lToken[nTokenOffset+1]', sCode)            # previous token
    sCode = re.sub(r"\bspell *[(]", '_oSpellChecker.isValid(', sCode)
    sCode = re.sub(r"\bbefore\(\s*", 'look(sSentence[:lToken[1+nTokenOffset]["nStart"]], ', sCode)          # before(sCode)
    sCode = re.sub(r"\bafter\(\s*", 'look(sSentence[lToken[nLastToken]["nEnd"]:], ', sCode)                 # after(sCode)
    sCode = re.sub(r"\bbefore0\(\s*", 'look(sSentence0[:lToken[1+nTokenOffset]["nStart"]], ', sCode)        # before0(sCode)
    sCode = re.sub(r"\bafter0\(\s*", 'look(sSentence0[lToken[nLastToken]["nEnd"]:], ', sCode)               # after0(sCode)
︙

Modified gc_core/py/lang_core/gc_functions.py from [9e52227dd2] to [8d220fa67a].

︙
147
148
149
150
151
152
153














154
155
156
157
158
159
160

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
173
174








+
+
+
+
+
+
+
+
+
+
+
+
+
+








            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


#### Analyse tokens for graph rules

def g_info (dToken):
    "for debugging: retrieve info of word"
    if not dToken:
        echo("> no token")
        return True
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph:
        echo("> not in dictionary: " + dToken["sValue"])
        return True
    for sKey, val in dToken.items():
        echo(sKey + ":" + str(val))
    return True


def g_value (dToken, sValues, nLeft=None, nRight=None):
    "test if <dToken['sValue']> is in sValues (each value should be separated with |)"
    sValue = "|"+dToken["sValue"]+"|"  if nLeft is None  else "|"+dToken["sValue"][slice(nLeft, nRight)]+"|"
    if sValue in sValues:
        return True
    if dToken["sValue"][0:2].istitle(): # we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
︙

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.005s