Grammalecte  Check-in [e6a7cd50a7]

Overview
Comment:[build] count unnamed rules
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | build
Files: files | file ages | folders
SHA3-256: e6a7cd50a78c4d141d1dc97150fb2bc1a5315f4aeca35be4bf6c297d3d63a552
User & Date: olr on 2017-05-16 23:52:20
Other Links: manifest | tags
Context
2017-05-17
00:59
[fr] nommage des règles du processeur check-in: 296e21eba6 user: olr tags: fr, trunk
2017-05-16
23:52
[build] count unnamed rules check-in: e6a7cd50a7 user: olr tags: build, trunk
23:46
[build] rename global vars check-in: a835df567d user: olr tags: build, trunk
Changes

Modified compile_rules.py from [e1c06fc5a9] to [9ba071ca61].

7
8
9
10
11
12
13

14
15
16
17
18
19
20
...
161
162
163
164
165
166
167

168
169
170
171
172
173
174
...
183
184
185
186
187
188
189


190
191
192
193
194
195
196
...
634
635
636
637
638
639
640


641
642
643
644
645
646
647
648
649
650
651
652
from distutils import file_util


dDEF = {}
lFUNCTIONS = []

aRULESET = set()     # set of rule-ids to check if there is several rules with the same id


dJSREGEXES = {}

sWORDLIMITLEFT  = r"(?<![\w.,–-])"   # r"(?<![-.,—])\b"  seems slower
sWORDLIMITRIGHT = r"(?![\w–-])"      # r"\b(?!-—)"       seems slower


................................................................................
        print(sRegex)
    return 0


def createRule (s, nIdLine, sLang, bParagraph, dOptPriority):
    "returns rule as list [option name, regex, bCaseInsensitive, identifier, list of actions]"
    global dJSREGEXES


    #### OPTIONS
    sLineId = str(nIdLine) + ("p" if bParagraph else "s")
    sRuleId = sLineId
    sOption = False         # False or [a-z0-9]+ name
    nPriority = 4           # Default is 4, value must be between 0 and 9
    tGroups = None          # code for groups positioning (only useful for JavaScript)
................................................................................
        sOption = m.group('option')[1:]  if m.group('option')  else False
        if m.group('ruleid'):
            sRuleId =  m.group('ruleid')[1:-1]
            if sRuleId in aRULESET:
                print("# Error. Several rules have the same id: " + sRuleId)
                exit()
            aRULESET.add(sRuleId)


        nPriority = dOptPriority.get(sOption, 4)
        if m.group('priority'):
            nPriority = int(m.group('priority')[1:])
        s = s[m.end(0):]
    else:
        print("# Warning. No option defined at line: " + sLineId)

................................................................................
        sPyCallables += "    return " + sReturn + "\n"
        sJSCallables += "    {}: function ({})".format(sFuncName, sParams) + " {\n"
        sJSCallables += "        return " + py2js(sReturn) + ";\n"
        sJSCallables += "    },\n"
    sJSCallables += "}\n"

    displayStats(lParagraphRules, lSentenceRules)



    d = { "callables": sPyCallables,
          "callablesJS": sJSCallables,
          "gctests": sGCTests,
          "gctestsJS": sGCTestsJS,
          "paragraph_rules": mergeRulesByOption(lParagraphRules),
          "sentence_rules": mergeRulesByOption(lSentenceRules),
          "paragraph_rules_JS": writeRulesToJSArray(mergeRulesByOption(lParagraphRulesJS)),
          "sentence_rules_JS": writeRulesToJSArray(mergeRulesByOption(lSentenceRulesJS)) }
    d.update(dOptions)

    return d







>







 







>







 







>
>







 







>
>












7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
...
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
...
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
...
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
from distutils import file_util


dDEF = {}
lFUNCTIONS = []

aRULESET = set()     # set of rule-ids to check if there is several rules with the same id
nRULEWITHOUTNAME = 0

dJSREGEXES = {}

sWORDLIMITLEFT  = r"(?<![\w.,–-])"   # r"(?<![-.,—])\b"  seems slower
sWORDLIMITRIGHT = r"(?![\w–-])"      # r"\b(?!-—)"       seems slower


................................................................................
        print(sRegex)
    return 0


def createRule (s, nIdLine, sLang, bParagraph, dOptPriority):
    "returns rule as list [option name, regex, bCaseInsensitive, identifier, list of actions]"
    global dJSREGEXES
    global nRULEWITHOUTNAME

    #### OPTIONS
    sLineId = str(nIdLine) + ("p" if bParagraph else "s")
    sRuleId = sLineId
    sOption = False         # False or [a-z0-9]+ name
    nPriority = 4           # Default is 4, value must be between 0 and 9
    tGroups = None          # code for groups positioning (only useful for JavaScript)
................................................................................
        sOption = m.group('option')[1:]  if m.group('option')  else False
        if m.group('ruleid'):
            sRuleId =  m.group('ruleid')[1:-1]
            if sRuleId in aRULESET:
                print("# Error. Several rules have the same id: " + sRuleId)
                exit()
            aRULESET.add(sRuleId)
        else:
            nRULEWITHOUTNAME += 1
        nPriority = dOptPriority.get(sOption, 4)
        if m.group('priority'):
            nPriority = int(m.group('priority')[1:])
        s = s[m.end(0):]
    else:
        print("# Warning. No option defined at line: " + sLineId)

................................................................................
        sPyCallables += "    return " + sReturn + "\n"
        sJSCallables += "    {}: function ({})".format(sFuncName, sParams) + " {\n"
        sJSCallables += "        return " + py2js(sReturn) + ";\n"
        sJSCallables += "    },\n"
    sJSCallables += "}\n"

    displayStats(lParagraphRules, lSentenceRules)

    print("Unnamed rules: " + str(nRULEWITHOUTNAME))

    d = { "callables": sPyCallables,
          "callablesJS": sJSCallables,
          "gctests": sGCTests,
          "gctestsJS": sGCTestsJS,
          "paragraph_rules": mergeRulesByOption(lParagraphRules),
          "sentence_rules": mergeRulesByOption(lSentenceRules),
          "paragraph_rules_JS": writeRulesToJSArray(mergeRulesByOption(lParagraphRulesJS)),
          "sentence_rules_JS": writeRulesToJSArray(mergeRulesByOption(lSentenceRulesJS)) }
    d.update(dOptions)

    return d