Merge 9447e0991b into 0b3dc9db21

docs/settings.rst

@@ -201,6 +201,7 @@ Also, you can use other file metadata attributes as well:
 * lang
 * author
 * category
+* post_id
 
 Example usage:
 

pelican/tests/test_contents.py

@@ -371,6 +371,21 @@ class TestArticle(TestPage):
         self.assertEqual(article.url, 'obrien/csharp-stuff/fnord/')
         self.assertEqual(article.save_as, 'obrien/csharp-stuff/fnord/index.html')
 
+    def test_slugify_post_id(self):
+        settings = get_settings()
+        settings['SLUG_SUBSTITUTIONS'] = [ ('C#', 'csharp') ]
+        settings['ARTICLE_URL'] = '{post_id}/{slug}/'
+        settings['ARTICLE_SAVE_AS'] = '{post_id}/{slug}/index.html'
+        article_kwargs = self._copy_page_kwargs()
+        article_kwargs['metadata']['author'] = "O'Brien"
+        article_kwargs['metadata']['category'] = 'C# & stuff'
+        article_kwargs['metadata']['title'] = 'fnord'
+        article_kwargs['metadata']['post_id'] = '10'
+        article_kwargs['settings'] = settings
+        article = Article(**article_kwargs)
+        self.assertEqual(article.url, '10/fnord/')
+        self.assertEqual(article.save_as, '10/fnord/index.html')
+
 
 class TestURLWrapper(unittest.TestCase):
     def test_comparisons(self):

pelican/tests/test_importer.py

@@ -32,7 +32,7 @@ class TestWordpressXmlImporter(unittest.TestCase):
 
     def test_ignore_empty_posts(self):
         self.assertTrue(self.posts)
-        for title, content, fname, date, author, categ, tags, kind, format in self.posts:
+        for title, content, fname, date, author, post_id, categ, tags, kind, format in self.posts:
             self.assertTrue(title.strip())
 
     def test_recognise_page_kind(self):
@@ -40,7 +40,7 @@ class TestWordpressXmlImporter(unittest.TestCase):
         self.assertTrue(self.posts)
         # Collect (title, filename, kind) of non-empty posts recognised as page
         pages_data = []
-        for title, content, fname, date, author, categ, tags, kind, format in self.posts:
+        for title, content, fname, date, author, post_id, categ, tags, kind, format in self.posts:
             if kind == 'page':
                 pages_data.append((title, fname))
         self.assertEqual(2, len(pages_data))

pelican/tools/pelican_import.py

@@ -124,6 +124,7 @@ def wp2fields(xml):
                 logger.warn('Post "%s" is lacking a proper title' % title)
 
             content = item.find('encoded').string
+            post_id = item.find('post_id').string
             filename = item.find('post_name').string
 
             if filename is None:
@@ -133,7 +134,7 @@ def wp2fields(xml):
             date_object = time.strptime(raw_date, "%Y-%m-%d %H:%M:%S")
             date = time.strftime("%Y-%m-%d %H:%M", date_object)
             author = item.find('creator').string
- 
+
             categories = [cat.string for cat in item.findAll('category', {'domain' : 'category'})]
             # caturl = [cat['nicename'] for cat in item.find(domain='category')]
 
@@ -143,7 +144,7 @@ def wp2fields(xml):
             if item.find('post_type').string == 'page':
                 kind = 'page'
 
-            yield (title, content, filename, date, author, categories, tags,
+            yield (title, content, filename, date, author, post_id, categories, tags,
                    kind, "wp-html")
 
 def dc2fields(file):
@@ -445,13 +446,15 @@ def build_header(title, date, author, categories, tags, slug):
     header += '\n'
     return header
 
-def build_markdown_header(title, date, author, categories, tags, slug):
+def build_markdown_header(title, date, author, post_id, categories, tags, slug):
     """Build a header from a list of fields"""
     header = 'Title: %s\n' % title
     if date:
         header += 'Date: %s\n' % date
     if author:
         header += 'Author: %s\n' % author
+    if post_id:
+        header += 'Post_ID: %s\n' % post_id
     if categories:
         header += 'Category: %s\n' % ', '.join(categories)
     if tags:
@@ -464,14 +467,14 @@ def build_markdown_header(title, date, author, categories, tags, slug):
 def fields2pelican(fields, out_markup, output_path,
         dircat=False, strip_raw=False, disable_slugs=False,
         dirpage=False, filename_template=None, filter_author=None):
-    for (title, content, filename, date, author, categories, tags,
+    for (title, content, filename, date, author, post_id, categories, tags,
             kind, in_markup) in fields:
         if filter_author and filter_author != author:
             continue
         slug = not disable_slugs and filename or None
         if (in_markup == "markdown") or (out_markup == "markdown") :
             ext = '.md'
-            header = build_markdown_header(title, date, author, categories, tags, slug)
+            header = build_markdown_header(title, date, author, post_id, categories, tags, slug)
         else:
             out_markup = "rst"
             ext = '.rst'