finalisation v5.0

colorapp/textPhonographer.py

 # -*- encoding:utf8 -*- 
-import re, sys, os, datetime, json, tempfile, csv, locale, pinyin
+import re, sys, os, datetime, json, tempfile, csv, locale, pinyin, pymongo
+from bson import json_util
 from colorapp.models import Entree, DicEntry, LogStat
 from collections import OrderedDict
 
@@ -26,8 +27,6 @@ api2classFile = "../phon2graph/data/api2class.json" # MANDARIN
 ########################################
 ########## CONNEXION MONGODB ###########
 ########################################
-import pymongo
-
 def connexion():
     mdp = ""
     with open('../private/dbmdp','r') as infile:
@@ -210,10 +209,19 @@ def traitement(mot, lang, liaison): # LIAISON : avec le caractere liaison en arg
         print("'", mot, "' trouvé dans le dico !",word2trans[mot])
         if lang in ["fr","en"]:
             transList = []
-            for trans, infos in word2trans[mot]['t'].items():
-                transList.append((trans.replace("_",""),infos['r'])) # SUPPRESSION SYMBOLE SYLLABE ICI '_'
-                print("TRANS",trans, trans.replace("_",""))
-                print("LOCS", infos['r'])
+            shortmem = [] # pour pas afficher plusieurs fois un même alignement (avec et sans syllabation typiquement; le visuel est identique)
+            for trans in word2trans[mot]['t']:
+                newT = trans['tt'].replace('.','')
+                if newT not in shortmem:
+                    transList.append((newT,trans['tr']))
+                    shortmem.append(newT)
+                else:
+                    for r in trans['tr']:
+                        # pour chaque région du trans courrant: si elle n'est pas dans les régions de la trans identique déjà présente dans transList: on l'ajoute
+                        # ci-dessous : alreadyPushedTuple correspond au tuple (newT,trans['r']) déjà présent dans transList, auquel on veut ajouter r
+                        if r not in [alreadyPushedTuple for alreadyPushedTuple in transList if alreadyPushedTuple[0]==newT][0][1]:
+                            [alreadyPushedTuple for alreadyPushedTuple in transList if alreadyPushedTuple[0]==newT][0][1].append(r)
+                print("TRANS",trans)
         result = []
 
         ############ partie d'appel de la fonction denasalisation
@@ -262,7 +270,7 @@ def traitementzh(mot):
     result = [] # liste type : [[car, api, phonlist, ton], [car, api, phonlist, ton]...]
 
     if mot in word2transZh.keys():
-        pinyinOutput = list(word2transZh[mot]["t"].keys())[0].lower()
+        pinyinOutput = word2transZh[mot]["t"][0]["tt"].lower()
         print("Mot trouvé dans le dictionnaire :", mot, pinyinOutput)
 
     else:
@@ -295,9 +303,14 @@ def getEntryByWord(m,mc,t,tc,lang):
     if lang == "fr":
         word2trans = word2transFr
         m = m.replace("'",'’')
+        dico = dicoFr
     elif lang == "en":
         word2trans = word2transEn
         m = m.replace('’',"'")
+        dico = dicoEn
+    elif lang == "zh":
+        word2trans = word2transZh
+        dico = dicoZh
 
     m = m.lower()
     t = t.replace('.','')
@@ -321,137 +334,149 @@ def getEntryByWord(m,mc,t,tc,lang):
     if tc == 'finit par' or tc == 'est égal à':
         tc2 = r'$'
 
-    for entree,transList in word2trans.items():
-        if re.match(mc1+m+mc2,entree):
-            transOK = False
-            for i,trans in enumerate(list(transList['t'].keys())):
-                if re.match(tc1+t+tc2,trans.replace('.','')):
-                    transOK = True
-            if transOK: result[entree] = transList
+    # for entree, infos in word2trans.items():
+    #     if re.match(mc1+m+mc2,entree):
+    #         transOK = False
+    #         for i,trans in enumerate(infos['t']):
+    #             if re.match(tc1+t+tc2,trans['t'].replace('.','')):
+    #                 transOK = True
+    #         if transOK: result[entree] = infos['t']
+
+    # Requêter directement MongoDB et envoyer l'ensemble des résultats (cétégories, traductions... compris)
+    for entree in dico.find({'w': {"$regex": mc1+m+mc2}}):
+        transOK = False
+        for i,trans in enumerate(entree['t']):
+            if re.match(tc1+t+tc2,trans['tt'].replace('.','')):
+                transOK = True
+        if transOK:
+            result[entree['w']] = {}
+            for i, j in entree.items():
+                if i != "_id":
+                    result[entree['w']][i] = j
     return sorted(result.items(), key=lambda M: locale.strxfrm(M[0])) # mise dans l'ordre alphabétique français (ex. é après e, et pas après z)
 
-def modifEntry(user,mot,newTransList,lang):
-    if lang == "fr":
+def modifEntry(user,mot,infos,lang):
+    if lang == "fr": 
         word2trans = word2transFr
+        dico = dicoFr
+    if lang == "en": 
+        word2trans = word2transEn
+        dico = dicoEn
+    if lang == "zh": 
+        word2trans = word2transZh
+        dico = dicoZh
 
-        newTransList = newTransList.split(',')
-        for ind,i in enumerate(newTransList):
-            newTransList[ind] = i.strip()
-        oldTransList = word2trans[mot]
-        if newTransList != oldTransList:
-            word2trans[mot] = newTransList
-            rewriteDico(lang)
-            writeLog(Type="MODIF", user=user, mot=mot, oldTransList=oldTransList, newTransList=newTransList, lang=lang)
-            print("Modification du dictionnaire par",user,": mot =",mot,"; oldTransList =",oldTransList,"; newTransList = ",newTransList)
-        return "Modification effectuée avec succès !"
+    oldInfos = dico.find_one({'w':mot})
+    
+    dico.update({"w":mot}, {"$set": infos})
+    word2trans[mot]['t'] = infos['t']
 
-    elif lang == "en":
-        word2trans = word2transEn
-        return "La modification du dictionnaire anglais n'est pas encore possible."
+    newlog = writeLog(Type="MODIF", user=user, mot=mot, oldMot=oldInfos, newMot=infos, lang=lang)
+    print("Modification du dictionnaire par",user,": lang =",lang,"; mot =",mot,"; oldMot =",oldInfos,"; newMot =",infos)
+    print("ICIIII newlog:",newlog)
+    return {"msg":"Modification effectuée avec succès !", "newlog":newlog}
 
 def addEntry(user,mot,trans,lang):
-    if lang == "fr":
+    if lang == "fr": 
         word2trans = word2transFr
-
+        dico = dicoFr
         trans = trans.replace('g','ɡ')
-        mot = mot.lower()
-        mot = mot.strip()
-        transList = trans.split(',')
-
-        for ind,i in enumerate(transList):
-            transList[ind] = i.strip()
-
-        if mot not in word2trans.keys():
-            word2trans[mot] = transList
-            rewriteDico("fr")
-            writeLog(Type="ADD", user=user, mot=mot, oldTransList="", newTransList=transList, lang="fr")
-            print("Modification du dictionnaire par",user,": ajout de mot =",mot,"; transList = ",transList)
-            return "Ajout effectué avec succès ! Merci pour votre participation !"
-        else:
-            return "Ce mot est déjà dans le dictionnaire !"
-    
-    elif lang == "en":
+        trans = trans.replace('r','ʁ')
+    if lang == "en": 
         word2trans = word2transEn
-        return "La modification du dictionnaire anglais n'est pas encore possible."
+        dico = dicoEn
+        trans = trans.replace('g','ɡ')
+    if lang == "zh": 
+        word2trans = word2transZh
+        dico = dicoZh
+
+    mot = mot.lower()
+    mot = mot.strip()
+    transList = trans.split(',')
+
+    for ind,i in enumerate(transList):
+        transList[ind] = i.strip()
+
+    if mot not in word2trans.keys():
+        newMot = {'t': []}
+        for t in transList:
+            if len(t)>0:
+                if lang =="fr":
+                    newMot['t'].append({ 'tt':t, 'tr':['FR']})
+                elif lang =="zh":
+                    newMot['t'].append({ 'tt':t, 'tr':['CN']})
+                else:
+                    newMot['t'].append({ 'tt':t, 'tr':[]})
+
+        if len(newMot['t'])>0:
+            word2trans[mot] = newMot
+            dico.insert_one({ 'w':mot, 't':newMot['t']})
+            newlog = writeLog(Type="ADD", user=user, mot=mot, oldMot="", newMot=transList, lang=lang)
+            return {"msg":"Ajout effectué avec succès ! Merci pour votre participation !", "newlog":newlog}
+        else:
+            return {"msg":"Transcription vide. Veuillez indiquer au moins une transcriptions phonétiques. Ajout annulé."}
+    else:
+        return {"msg":"Ce mot est déjà dans le dictionnaire !"}
 
 def delEntry(user,mot,lang):
-    if lang == "fr":
+    if lang == "fr": 
         word2trans = word2transFr
-    
-        if mot in word2trans.keys():
-            word2trans.pop(mot)
-            if lang == "fr":
-                rewriteDico('fr')
-                writeLog(Type="DEL", user=user, mot=mot, oldTransList="", newTransList="",lang="fr")
-            if lang == "en":
-                rewriteDico('en')
-                writeLog(Type="DEL", user=user, mot=mot, oldTransList="", newTransList="",lang="en")
-            print("Modification du dictionnaire par",user,": suppression de mot =",mot)
-        return "Suppression effectuée avec succès."
-
-    elif lang == "en":
+        dico = dicoFr
+    if lang == "en": 
         word2trans = word2transEn
-        return "La modification du dictionnaire anglais n'est pas encore possible."
+        dico = dicoEn
+    if lang == "zh": 
+        word2trans = word2transZh
+        dico = dicoZh
+    
+    if mot in word2trans.keys():
+        oldmot = word2trans[mot]
+        word2trans.pop(mot)
+        dico.delete_one({'w':mot})
+        newlog = writeLog(Type="DEL", user=user, mot=mot, oldMot=oldmot, newMot="",lang=lang)
+        print("Modification du dictionnaire par",user,": suppression de mot =",mot)
+    
+        return {"msg":"Suppression effectuée avec succès.", "newlog":newlog}
 
 
-def rewriteDico(lang):
+def sendMeLogPlease(lang):
     if lang == "fr":
-        word2trans = word2transFr
-        print("REWRITE DICO FR")
-        '''
-        print('Rewritting dictionary...')
-        with tempfile.NamedTemporaryFile(dir='.', delete=False, mode="w") as tmp:
-            json.dump(word2trans, tmp, ensure_ascii=False)
-            os.replace(tmp.name, dicFileFr)
-        print('Dico rewritten.')
-        '''
-
+        logDic = dicoFrLogs
     elif lang == "en":
-        word2trans = word2transEn
-        return "La modification du dictionnaire anglais n'est pas encore possible."
+        logDic = dicoEnLogs
+    elif lang == "zh":
+        logDic = dicoZhLogs
     
+    rep = []
+    for log in logDic.find():
+        rep.append(noIdDict(log))
 
-def sendMeLogPlease(lang):
-    if lang == "fr":
-        return logDicFr
-    elif lang == "en":
-        return logDicEn
+    return rep
 
-def writeLog(Type,user,mot,oldTransList,newTransList,lang):
+def noIdDict(dic):
+    if type(dic) is dict:
+        # renvoit un dic sans la clé "_id"
+        return { i:j for i,j in dic.items() if i!='_id' }
+    else:
+        return dic
+
+def writeLog(Type,user,mot,oldMot,newMot,lang):
     if lang == "fr":
-        logDic = logDicFr
+        logDic = dicoFrLogs
     elif lang == "en":
-        logDic = logDicEn
+        logDic = dicoEnLogs
+    elif lang == "zh":
+        logDic = dicoZhLogs
 
-    now = datetime.datetime.now()
-    date = "{}-{}-{} {}:{}:{}".format(now.year, now.month, now.day, now.hour, now.minute, now.second)
-    
-    if mot not in logDic.keys(): logDic[mot] = []
-    logDic[mot].append({
-        "date":date,
+    newlog = {
+        "date":datetime.datetime.now(),
         "user":user,
-        "oldTransList":oldTransList,
-        "newTransList":newTransList,
-        "Type":Type
-    })
-    
-    with tempfile.NamedTemporaryFile(dir='.', delete=False, mode="w") as tmp:
-        json.dump(logDic, tmp, ensure_ascii=False, indent=4)
-        if lang == "fr":
-            os.replace(tmp.name, logFile)
-        elif lang == "en":
-            os.replace(tmp.name, logFileEn)
-    print("Log file updated.")
-
-def writeLogBugs(mot, lang):
-    now = datetime.datetime.now()
-    date = "{}-{}-{} {}:{}:{}".format(now.year, now.month, now.day, now.hour, now.minute, now.second)
+        "word":mot,
+        "old":noIdDict(oldMot),
+        "new":noIdDict(newMot),
+        "type":Type
+    }
+    logDic.insert_one(newlog)
     
-    logBug[mot] = date
-    with tempfile.NamedTemporaryFile(dir='.', delete=False, mode="w") as tmp:
-        json.dump(logBug, tmp, ensure_ascii=False, indent=4)
+    print("New log: lang={} ; user={} ; word={} ; type={}".format(lang,user,mot,Type))
+    return noIdDict(newlog)
\ No newline at end of file
-        if lang == "fr":
-            os.replace(tmp.name, logBugFile)
-        elif lang == "en":
-            os.replace(tmp.name, logBugFileEn)
-    print("Log file updated.")
\ No newline at end of file

colorapp/views.py

@@ -214,7 +214,7 @@ def getPhonoOf(request):
 def updateTime():
     upd = str(subprocess.check_output(["git", "log", "-1", "--format=%cd", "--date=short"]))
     #ver = str(subprocess.check_output(["git", "rev-list", "--all", "--count"]))
-    return 'Version 4.0 (mis à jour le '+upd[2:-3]+')'
+    return 'Version 5.0 (mis à jour le '+upd[2:-3]+')'
 
 def main0(request):
     data = Data()
@@ -250,6 +250,14 @@ def dicoViewEn(request):
     data.dicoLang = "en"
     return render(request, 'editDico.html', {'data': data})
 
+def dicoViewZh(request):
+    data = Entree()
+    data.update = updateTime()
+    data.lenDic = txtphono.getLenDicZh()
+    data.logStat = txtphono.getLogStat('zh')
+    data.dicoLang = "zh"
+    return render(request, 'editDico.html', {'data': data})
+
 def dicoReq(request):
     dicoLang = request.GET.get('dicoLang', None)
     mot = request.GET.get('mot', None)
@@ -271,34 +279,31 @@ def get_client_ip(request):
     return ip
 
 def editEntry(request):
-    mot = request.GET.get('mot', None)
-    lang = request.GET.get('lang', None)
-    transList = request.GET.get('transList', None)
+    colis = json.loads(request.body)
+    mot = colis['mot']
+    lang = colis['lang']
+    infos = colis['infos']
+    print(infos)
     ipCli = get_client_ip(request)
-    rep = {
-        'reponse': txtphono.modifEntry(ipCli,mot,transList,lang)
-    }
-    return JsonResponse(rep)
+
+    return JsonResponse(txtphono.modifEntry(ipCli,mot,infos,lang))
 
 def newEntry(request):
     mot = request.GET.get('mot', None)
     trans = request.GET.get('trans', None)
     lang = request.GET.get('lang', None)
     ipCli = get_client_ip(request)
-    rep = {
-        'reponse': txtphono.addEntry(ipCli,mot,trans,lang)
-    }
-    return JsonResponse(rep)
+
+    return JsonResponse(txtphono.addEntry(ipCli,mot,trans,lang))
 
 def supprEntry(request):
     mot = request.GET.get('mot', None)
     lang = request.GET.get('lang', None)
     ipCli = get_client_ip(request)
-    rep = {
-        'reponse': txtphono.delEntry(ipCli,mot,lang)
-    }
-    return JsonResponse(rep)
+
+    return JsonResponse(txtphono.delEntry(ipCli,mot,lang))
 
 def getLog(request):
-    rep = txtphono.sendMeLogPlease('fr')
-    return JsonResponse(rep)
+    lang = request.GET.get('lang', None)
+    rep = txtphono.sendMeLogPlease(lang)
\ No newline at end of file
+    return JsonResponse({"logs":rep})
\ No newline at end of file

coloriseur/urls.py

@@ -31,8 +31,9 @@ urlpatterns = [
     path('app/dico/', colorapp_views.dicoView),
     path('app/dico/fr', colorapp_views.dicoViewFr),
     path('app/dico/en', colorapp_views.dicoViewEn),
+    path('app/dico/zh', colorapp_views.dicoViewZh),
     path('dicoSearch/', colorapp_views.dicoReq),
-    path('editEntry/', colorapp_views.editEntry),
+    path('editEntry/', csrf_exempt(colorapp_views.editEntry)),
     path('addEntry/', colorapp_views.newEntry),
     path('delEntry/', colorapp_views.supprEntry),
     path('getLog/', colorapp_views.getLog)

static/languages/languages.js

@@ -96,9 +96,9 @@ var langJson = {
         "zh": ""
     },
     "sp_infoWiki": {
-        "fr": "WikiColor est un coloriseur automatique de texte basé sur les transcriptions phonétiques du Wiktionnaire et de la collaboration de nombreux utilisateurs. Vous pouvez consulter et participer à l'amélioration du dictionnaire en cliquant sur le bouton ci-dessous. L'alignement phono-graphémique reste encore expérimental, toute suggestion de votre part est bienvenue ! N'hésitez pas à visiter <a href='https://alem.hypotheses.org/outils-alem-app/wikicolor'>notre site</a>, et participez aux discussions sur <a href='https://groups.google.com/forum/#!forum/alem-app'>le forum</a>.",
-        "en": "WikiColor is an automatic text coloriser based on Wiktionary's phonetic transcriptions, CMU Pronunciation Dictionary and collaboration of our users community. English dictionary isn't editable yet, but it will be soon! Phono-graphemic alignment still is experimental, especially for English, any suggestion from you will be welcome! We are still working on the phonological representation of English, which is a big challenge. Please let us know your suggestions in <a href='https://groups.google.com/forum/#!forum/alem-app'>our Forum</a>. We also have <a href='https://alem.hypotheses.org/outils-alem-app/wikicolor'>a website</a> (English content will come soon!).",
-        "zh": "WikiColor is an automatic text coloriser based on Wiktionary's phonetic transcriptions, CMU Pronunciation Dictionary and collaboration of our users community. English dictionary isn't editable yet, but it will be soon! Phono-graphemic alignment still is experimental, especially for English, any suggestion from you will be welcome! We are still working on the phonological representation of English, which is a big challenge. Please let us know your suggestions in <a href='https://groups.google.com/forum/#!forum/alem-app'>our Forum</a>. We also have <a href='https://alem.hypotheses.org/outils-alem-app/wikicolor'>a website</a> (English content will come soon!)."
+        "fr": "WikiColor est un coloriseur automatique de texte basé sur les transcriptions phonétiques du Wiktionnaire, du <a href='https://repository.ortolang.fr/api/content/morphalou/2/LISEZ_MOI.html' target='_blank'>lexique Morphalou3.1</a> et de la collaboration de nombreux utilisateurs. Vous pouvez consulter et participer à l'amélioration du dictionnaire en cliquant sur le bouton ci-dessous. L'alignement phono-graphémique reste encore expérimental, toute suggestion de votre part est bienvenue ! N'hésitez pas à visiter <a href='https://alem.hypotheses.org/outils-alem-app/wikicolor'>notre site</a>, et participez aux discussions sur <a href='https://groups.google.com/forum/#!forum/alem-app'>le forum</a>.",
+        "en": "WikiColor is an automatic text coloriser based on Wiktionary's phonetic transcriptions, <a href='http://www.speech.cs.cmu.edu/cgi-bin/cmudict/?in=pronunciation&stress=-s' target='_blank'>CMU Pronouncing Dictionary</a>, <a href='https://github.com/JoseLlarena/Britfone' target='_blank'>Britfone Pronunciation Dictionary</a> and collaboration of our users community. Please consider to add words and spellings to our word base! Phono-graphemic alignment still is experimental, especially for English, any suggestion from you will be welcome! We are still working on the phonological representation of English, which is a big challenge. Please let us know your suggestions in <a href='https://groups.google.com/forum/#!forum/alem-app'>our Forum</a>. We also have <a href='https://alem.hypotheses.org/outils-alem-app/wikicolor'>a website</a> (English content will come soon!).",
+        "zh": "WikiColor is an automatic text coloriser based on <a href='https://cc-cedict.org/wiki/' target='_blank'>the CC-CEdict Dictionnary</a>, the Python phonetiser <a href='https://pypi.org/project/pinyin/' target='_blank'>Pinyin0.4.0</a> and collaboration of our users community. Please consider to add words and spellings to our word base! Please let us know your suggestions in <a href='https://groups.google.com/forum/#!forum/alem-app'>our Forum</a>. We also have <a href='https://alem.hypotheses.org/outils-alem-app/wikicolor'>a website</a> (English content will come soon!)."
     },
     "sp_btnEditDico": {
         "fr": "Consulter/éditer le dictionnaire",