Merge pull request #44 from oscar-defelice/master

Added the French language support

Author: filyp

.gitignore

@@ -4,3 +4,4 @@ MANIFEST
 .vscode
 autocorrect/data/*
 .coverage
+.DS_Store

README.md

@@ -62,6 +62,10 @@ bzip2 -d ruiwiki-latest-pages-articles.xml.bz2
 
 After that:
 
+First, edit the `autocorrect.constants` dictionaries in order to accommodate regexes and dictionaries for your language.
+
+Then:
+
 ```python
 >>> from autocorrect.word_count import count_words
 >>> count_words('ruwiki-latest-pages-articles.xml', 'ru')

autocorrect/constants.py

@@ -9,6 +9,7 @@
     "cs": r"[AÁBCČDĎEÉĚFGH(Ch)IÍJKLMNŇOÓPQRŘSŠTŤUÚŮVWXYÝZŽaábcčdďeéěfgh(ch)iíjklmnňoópqrřsštťuúůvwxyýzž]+",
     "el": r"[α-ωΑ-ΩίϊΐόάέύϋΰήώΊΪΪ́ΌΆΈΎΫΫ́ΉΏ]+",
     "it": r"[a-zA-ZãáàâçéêíõóôúüÃÁÀÂÇÉÊÍÕÓÔÚÜ]+",
+    "fr": r"[a-zA-ZãáàâçéêíõóôúüÃÁÀÂÇÉÊÍÕÓÔÚÜ]+",
     "vi": r"[a-zA-ZàáạảãÀÁẠẢÃằắặẳẵẰẮẶẲẴầấậẩẫẦẤẬẨẪèéẹẻẽÈÉẸẺẼềếệểễỀẾỆỂỄìíịỉĩÌÍỊỈĨòóọỏõÒÓỌỎÕồốộổỗỒỐỘỔỖờớợởỡỜỚỢỞỠùúụủũÙÚỤỦŨừứựửữỪỨỰỬỮỳýỵỷỹỲÝỴỶỸ]+",
 }
 
@@ -23,13 +24,15 @@
     "cs": "aábcčdďeéěfgh(ch)iíjklmnňoópqrřsštťuúůvwxyýzž",
     "el": "αβγδεζηθικλμνξοπρςτυφχψωίϊΐόάέύϋΰήώ",
     "it": "abcdefghijklmnopqrstuvwxzyãáàâçéêíõóôúü",
+    "fr": "abcdefghijklmnopqrstuvwxzyãáàâçéêíõóôúü",
     "vi": "aàảãáạăằẳẵắặâầẩẫấậbcdđeèẻẽéẹêềểễếệfghiìỉĩíịjklmnoòỏõóọôồổỗốộơờởỡớợpqrstuùủũúụưừửữứựvwxyỳỷỹýỵz",
 }
 
 ipfs_gateways = [
     "http://ipfs.io/ipfs/",
     "https://gateway.pinata.cloud/ipfs/",
-    "https://cf-ipfs.com/ipfs/",  # this one has the best performance, but doesn't return download progress
+    # this one has the best performance, but doesn't return download progress
+    "https://cf-ipfs.com/ipfs/",
 ]
 
 ipfs_paths = {
@@ -43,6 +46,7 @@
     "pt": ["QmbRSZvfJV6zN12zzWhecphcvE9ZBeQdAJGQ9c9ttJXzcg/pt.tar.gz"],
     "el": ["QmbRSZvfJV6zN12zzWhecphcvE9ZBeQdAJGQ9c9ttJXzcg/el.tar.gz"],
     "it": ["QmbRSZvfJV6zN12zzWhecphcvE9ZBeQdAJGQ9c9ttJXzcg/it.tar.gz"],
+    "fr": ["QmPRNDmUDTXikq8gWnGcw3ZGmnoBfvekmAyeyX8y6onf23/fr.tar.gz"],
     "vi": ["QmRRJj5i7nkpzTRSKhFe23XMjLRw7f2zD6FLKDrRfzco7f/vi.tar.gz"],
 }
 
@@ -82,4 +86,5 @@
     "it": [
         "https://dl.dropboxusercontent.com/s/6xci1wfb387zk23/it.tar.gz?dl=0",
     ],
+    "fr": ["https://mega.nz/file/kQByQJAb#rMbmF0HG09MLQQ-FDafHrPAgXigJIpmC1zhtxRMp2dQ"],
 }

setup.py

@@ -24,6 +24,7 @@
         "Natural Language :: Portuguese",
         "Natural Language :: Greek",
         "Natural Language :: Italian",
+        "Natural Language :: French",
         "Natural Language :: Vietnamese",
         "Programming Language :: Python",
         "Programming Language :: Python :: 3",

test_all.py

@@ -127,6 +127,19 @@
     "salto": "saulto",
 }
 
+french_words_all_correct = {
+    "ordre": "oldre",
+    "leger": "lezger",
+    "cahier": "cnhier",
+    "saut": "slaut",
+    "vache": "vacne",
+    "fromage": "fromae",
+    "bisous": "biosus",
+    "possible": "possable",
+    "position": "posizion",
+    "populaire": "popularie",
+}
+
 single_typos_me = {
     "ae",
     "ame",
@@ -1009,6 +1022,38 @@
         "cavallo": "cavatlo",
         "poltrona": "poltrola",
     },
+    "fr": {
+        "disparu": "disparue",
+        "atteint": "atteind",
+        "croient": "croyent",
+        "cicogne": "cygogne",
+        "electronique": "électronique",
+        "bien": "bein",
+        "connexion": "connection",
+        "galerie": "gallerie",
+        "meilleur": "meiileur",
+        "obnubiler": "obnibuler",
+        "oculaire": "ocualire",
+        "télescope": "teiescope",
+        "valeur": "vaelur",
+        "vertu": "veltu",
+        "salade": "saiade",
+        "renommer": "renomner",
+        "sibyllin": "sibuliin",
+        "successeur": "succaszeur",
+        "écologie": "ecoiogie",
+        "éloge": "elogie",
+        "emménager": "ennenager",
+        "cheval": "clreval",
+        "permis": "pennis",
+        "recueillir": "recuelilir",
+        "martel": "manel",
+        "veux": "vuex",
+        "emploi": "emnloi",
+        "pôle": "pole",
+        "qui": "uui",
+        "experience": "escpehience",
+    },
     "vi": {
         "hiếu": "hiéu",
         "hiền": "hién",
@@ -1141,6 +1186,11 @@ def test_italian():
     assert spelltest(spell_it, italian_words_all_correct) == 0
 
 
+def test_french():
+    spell_fr = Speller("fr")
+    assert spelltest(spell_fr, french_words_all_correct) == 0
+
+
 if __name__ == "__main__":
     command = sys.argv[1]
 
@@ -1161,6 +1211,8 @@ def test_italian():
         benchmark("spanish words", spell, optional_language_tests["es"])
         spell = Speller("it")
         benchmark("italian words", spell, optional_language_tests["it"])
+        spell = Speller("fr")
+        benchmark("french words", spell, optional_language_tests["fr"])
     elif command == "find_threshold":
         lang = sys.argv[2]
         test = optional_language_tests[lang]