Add "alternative_spellings" property + minor bug fix for words with alternative spellings in title

Makefile

@@ -45,4 +45,5 @@ update-test-data:
 	./run_duden.py --export Kragen > tests/test_data/Kragen.yaml
 	./run_duden.py --export Petersilie > tests/test_data/Petersilie.yaml
 	./run_duden.py --export einfach -r1 > tests/test_data/einfach.yaml
-	./run_duden.py --export Keyboard > tests/test_data/Keyboard.yaml
+	./run_duden.py --export Keyboard > tests/test_data/Keyboard.yaml
+	./run_duden.py --export Meme > tests/test_data/Meme.yaml

completions/duden

@@ -23,6 +23,7 @@ _duden () {
         --no-cache
         --export
         --phonetic
+        --alternative-spellings
     )
     opts_with_arg=(
         -r --result

completions/duden.fish

@@ -1 +1 @@
-complete -c duden -xa "-h --help --title --name --article --part-of-speech --frequency --usage --word-separation --meaning-overview --synonyms --origin --compounds -g --grammar -r --result --fuzzy --version --no-cache --export --phonetic"
+complete -c duden -xa "-h --help --title --name --article --part-of-speech --frequency --usage --word-separation --meaning-overview --synonyms --origin --compounds -g --grammar -r --result --fuzzy --version --no-cache --export --phonetic --alternative-spellings"

duden/cli.py

@@ -55,6 +55,9 @@ def display_word(word, args):
     elif args.phonetic:
         if word.phonetic:
             print(word.phonetic)
+    elif args.alternative_spellings:
+        if word.alternative_spellings:
+            print(word.alternative_spellings)
     elif args.grammar:
         display_grammar(word, args.grammar)
     elif args.export:
@@ -119,6 +122,8 @@ def parse_args():
                         help=_('print program version'))
     parser.add_argument('--phonetic', action='store_true',
                         help=_('display pronunciation'))
+    parser.add_argument('--alternative-spellings', action='store_true',
+                        help=_('display alternative spellings'))
 
     return parser.parse_args()
 

duden/display.py

@@ -152,3 +152,6 @@ def describe_word(word):
         for part_of_speech, words in word.compounds.items():
             print(blue(' - {}:'.format(part_of_speech.capitalize())),
                   ', '.join(words))
+
+    if word.alternative_spellings:
+        print(white(_('Alternative spellings:'), bold=True), word.alternative_spellings)

duden/word.py

@@ -14,7 +14,7 @@
 EXPORT_ATTRIBUTES = [
     'name', 'urlname', 'title', 'article', 'part_of_speech', 'usage',
     'frequency', 'word_separation', 'meaning_overview', 'origin', 'compounds',
-    'grammar_raw', 'synonyms', 'words_before', 'words_after', 'phonetic'
+    'grammar_raw', 'synonyms', 'words_before', 'words_after', 'phonetic', 'alternative_spellings'
 ]
 
 gettext.install('duden', os.path.join(os.path.dirname(__file__), 'locale'))
@@ -53,12 +53,20 @@ def name(self):
         """
         Word without article
         """
+
+        # Find span with class "lemma__main"
+        title_element = self.soup.find('span', {"class": "lemma__main"})
+        if title_element is not None:
+            # remove soft hyphens "\xad" and return
+            return clear_text(title_element.get_text())
+
+        #  if the title_element does not exist, we fall back to the old method
         if self.part_of_speech is not None and 'Substantiv' not in self.part_of_speech:
             return self.title
         if ', ' not in self.title:
             return self.title
 
-        name, _ = self.title.split(', ')
+        name, _ = self.title.split(', ', 1)
         return name
 
     @property
@@ -88,12 +96,19 @@ def article(self):
         """
         Word article
         """
+        # Find span with class "lemma__determiner"
+        article_element = self.soup.find('span', {"class": "lemma__determiner"})
+        if article_element is not None:
+            # remove soft hyphens "\xad" and return
+            return article_element.get_text().replace('\xad', '').strip()
+
+        #  if the article_element does not exist, we fall back to the old method
         if self.part_of_speech is not None and 'Substantiv' not in self.part_of_speech:
             return None
         if ', ' not in self.title:
             return None
 
-        _, article = self.title.split(', ')
+        _, article = self.title.split(', ', 1)
         return article
 
     def _find_tuple_dl(self, key, element=None):
@@ -357,3 +372,14 @@ def phonetic(self):
             return ipa.get_text()
 
         return None
+
+    @property
+    def alternative_spellings(self):
+        """
+        Returns alternate spellings
+        """
+        alternative_spellings = self.soup.find_all('span', {"class": "lemma__alt-spelling"})
+        if alternative_spellings is None:
+            return None
+
+        return [spelling.get_text() for spelling in alternative_spellings]

tests/test_data/Barmherzigkeit.yaml

@@ -42,3 +42,4 @@ words_after:
 - Bar-Mizwa
 - Bar-Mizwa
 phonetic: null
+alternative_spellings: []

tests/test_data/Feiertag.yaml

@@ -81,3 +81,4 @@ words_after:
 - Feiertagsruhe
 - Feiertagsstille
 phonetic: null
+alternative_spellings: []

tests/test_data/Keyboard.yaml

@@ -54,3 +54,4 @@ words_after:
 - Keyboardspielerin
 - Keylogger
 phonetic: '[ˈkiːbɔːɐ̯t]'
+alternative_spellings: []

tests/test_data/Kragen.yaml

@@ -34,3 +34,4 @@ words_after:
 - kragenlos
 - Kragennummer
 phonetic: null
+alternative_spellings: []

tests/test_data/Meme.yaml

@@ -0,0 +1,31 @@
+name: Meme
+urlname: Meme
+title: Meme, auch Mem, das
+article: das
+part_of_speech: Substantiv, Neutrum
+usage: null
+frequency: 1
+word_separation:
+- Meme, Mem
+meaning_overview: (interessantes oder witziges) Bild, Video o. Ä., das in sozialen
+  Netzwerken schnell und weit verbreitet wird
+origin: englisch meme, eigentlich = weit verbreitete Idee o. Ä., zu griechisch mnḗmē =
+  Gedächtnis
+compounds: null
+grammar_raw: []
+synonyms: null
+words_before:
+- Membra
+- Membran
+- Membrane
+- Membranofon
+- Membrum
+words_after:
+- Memel
+- Memel
+- Memeler
+- Memeler
+- Memelerin
+phonetic: '[miːm]'
+alternative_spellings:
+- Mem

tests/test_data/Petersilie.yaml

@@ -56,3 +56,4 @@ words_after:
 - Petersilienwurzel
 - Peterskirche
 phonetic: '[petɐˈziːli̯ə]'
+alternative_spellings: []

tests/test_data/Qat.yaml

@@ -25,3 +25,4 @@ words_after:
 - qdm
 - q. e. d.
 phonetic: '[kat]'
+alternative_spellings: []

tests/test_data/einfach.yaml

@@ -59,3 +59,4 @@ words_after:
 - einfachgesetzlich
 - Einfachheit
 phonetic: '[ˈaɪ̯nfax]'
+alternative_spellings: []

tests/test_data/laufen.yaml

@@ -233,3 +233,4 @@ words_after:
 - Läufer
 - Lauferei
 phonetic: null
+alternative_spellings: []