add file for schema and continue models.py

grnx/models.py

@@ -39,17 +39,33 @@ def json_handler(obj):
         raise TypeError('Object of type %s with value of %s is not JSON serializable' % (type(obj), repr(obj)))
 
 
+def split(file_path):
+    return os.path.normpath(file_path).split(os.sep)
+
+
 class Article(object):
 
     def __init__(self, path, content, publication_date=None):
         self.path = path
         self.content = content
 
-        split_path = os.path.normpath(path).split(os.sep)
+        split_path = split(path)
 
-        self.filename = split_path[-1:]     # the last element
+        self.filename = split_path[-1]     # the last element
+        self.filename_without_extension = os.path.splitext(self.filename)[0]
         self.publication_date = get_date_from_article_filename(self.filename)
-        self.slug = slugify(self.filename)
+
+        self.slug = self.filename_without_extension
+
+        if self.publication_date:
+            self.slug = self.slug.replace(
+                self.publication_date.strftime('%Y-%m-%d'), ''
+            )
+
+        if self.slug and self.slug.startswith('-'):
+            self.slug = self.slug[1:]
+
+        self.slug = slugify(self.slug)
 
         try:
             self.category = split_path[1]       #
@@ -79,13 +95,13 @@ def get_date_from_article_filename(article_filename):
         2017-02-03-divinity-origin-sin.md -> None
         lynis.md -> None
     """
-    values = article_filename.split('-')
+    values = article_filename[0:10]
 
     date = None
     try:
-        date = datetime.date(int(values[0]), int(values[1]), int(values[2]))
+        date = datetime.datetime.strptime(values, '%Y-%m-%d').date()
     except (ValueError, TypeError):
-        logger.warn('Ignoring file - no publication date found %s', article_filename)
+        logger.warn('No publication date found %s', article_filename)
 
     return date
 
@@ -105,7 +121,10 @@ class Site(object):
 
         for root, *_, files in os.walk(root_path):
             for file in [file for file in files if file.endswith(".md")]:
-                self.build_article(root, file)
+                try:
+                    self.build_article(root, file)
+                except UnicodeDecodeError:
+                    continue
 
     def build_article(self, filepath, filename):
         """Build a new article from an existing file.
@@ -120,32 +139,36 @@ class Site(object):
             None if no publication date can be built.
             An `grnx.models.Article` instance instead.
         """
-        publication_date = get_date_from_article_filename(filename)
-        if not publication_date:
-            return
+
+        article_file_path = os.path.join(filepath, filename)
 
         article = None
-        with open(os.path.join(filepath, filename), encoding="utf8") as f:
+        with open(article_file_path, encoding="utf8") as f:
             content = f.read()
 
-            article = Article(filepath, content, publication_date)
+            article = Article(article_file_path, content)
 
-        logger.warn('article found in %s: %s', article.category, article)
+        if article:
+            logger.warn('article found in %s: %s', article.category, article)
 
-        self.articles.append(article)
+            self.articles.append(article)
 
-        if article.category not in self.categories:
-            self.categories[article.category] = []
+            if article.category not in self.categories:
+                self.categories[article.category] = []
 
-        self.categories[article.category].append(article)
+            self.categories[article.category].append(article)
 
         return article
 
     def to_json(self):
         """Serialize the content of the current structure to JSON format."""
 
-        json_dumps = json.dumps(self, default=json_handler, sort_keys=True, indent=4)
-        print('json result: ' + json_dumps)
+        json_dumps = json.dumps(
+            self,
+            default=json_handler,
+            sort_keys=True,
+            indent=4
+        )
         return json_dumps
 
     def serialize(self):

requirements.txt

@@ -4,4 +4,5 @@ clize==4.0.3
 pytest==3.7.2
 pytest-cov==2.5.1
 jinja==2.10
-python-slugify==1.2.5
+python-slugify==1.2.5
+markdown==2.6.11

tests/test_models.py

@@ -2,16 +2,26 @@
 
 from datetime import date
 
-from grnx.models import get_date_from_article_filename
+from grnx.models import get_date_from_article_filename, split
 from grnx.models import Article
 
 
+def test_split_path():
+    assert split('articles/sys/2018-01-01 Scaleway Review.md') == ['articles', 'sys', '2018-01-01 Scaleway Review.md']
+
+
+def test_filename():
+    article = Article("2019-01-01-blabla.md", "")
+    assert "2019-01-01-blabla" == article.filename_without_extension
+    assert "2019-01-01-blabla.md" == article.filename
+
 def test_article_match_date():
     """Checks that a date can be extracted from a filename."""
 
     assert get_date_from_article_filename('2018-09-01-test.md') == date(2018, 9, 1)
     assert get_date_from_article_filename('2017-02-30-divinity-origin-sin.md') == None
     assert get_date_from_article_filename('lynis.md') == None
+    assert get_date_from_article_filename('2018-01-01 scaleway-review.md') == date(2018, 1, 1)
 
 
 def test_article_slug():
@@ -42,3 +52,12 @@ def test_article_keywords():
     article = Article('articles/dev/2019-01-01-blabla.md', "")
 
     assert len(article.keywords) == 0
+
+
+def test_article_properties():
+    article = Article('articles/dev/python/django/2019-01-01-blabla.md', "")
+
+    assert article.filename == '2019-01-01-blabla.md'
+    assert article.filename_without_extension == '2019-01-01-blabla'
+    assert article.slug == 'blabla'
+    assert article.publication_date == date(2019, 1, 1)