ci/prepare-documentation.py: factor out the Markdown parsing code int…

…o a module

I plan to add more scripts that reuse this logic. Another benefit of this is
that it'll let us switch out the underlying Markdown parser if mistune proves
unsatisfactory.

ci/lib/omzdocs.py

@@ -0,0 +1,58 @@
+# Copyright (c) 2021 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import collections
+
+import mistune
+
+_parse_markdown = mistune.create_markdown(renderer=mistune.AstRenderer())
+
+def _get_all_ast_nodes(ast_nodes):
+    for node in ast_nodes:
+        yield node
+        if 'children' in node:
+            # workaround for https://github.com/lepture/mistune/issues/269
+            if isinstance(node['children'], str):
+                yield {'type': 'text', 'text': node['children']}
+            else:
+                yield from _get_all_ast_nodes(node['children'])
+
+def _get_text_from_ast(ast_nodes):
+    def get_text_from_node(node):
+        if node['type'] != 'text':
+            raise RuntimeError(f'unsupported node type: {node["type"]}')
+        return node['text']
+
+    return ''.join(map(get_text_from_node, ast_nodes))
+
+ExternalReference = collections.namedtuple('ExternalReference', ['type', 'url'])
+
+class DocumentationPage:
+    def __init__(self, markdown_text):
+        self._ast = ast = _parse_markdown(markdown_text)
+
+        self._title = None
+        if ast and ast[0]['type'] == 'heading' and ast[0]['level'] == 1:
+            self._title = _get_text_from_ast(ast[0]['children'])
+
+    @property
+    def title(self):
+        return self._title
+
+    def external_references(self):
+        for node in _get_all_ast_nodes(self._ast):
+            if node['type'] == 'image':
+                yield ExternalReference('image', node['src'])
+            elif node['type'] == 'link':
+                yield ExternalReference('link', node['link'])

ci/prepare-documentation.py

@@ -39,17 +39,21 @@
 import logging
 import re
 import shutil
+import sys
 import urllib.parse
 import urllib.request
 import xml.etree.ElementTree as ET
 
 from pathlib import Path
 
-import mistune
 import yaml
 
 OMZ_ROOT = Path(__file__).resolve().parents[1]
 
+sys.path.append(str(OMZ_ROOT / 'ci/lib'))
+
+import omzdocs
+
 XML_ID_ATTRIBUTE = '{http://www.w3.org/XML/1998/namespace}id'
 
 # For most task types, taking the machine-readable form and replacing
@@ -63,29 +67,6 @@
     'text_to_speech': 'Text-to-speech',
 }
 
-parse_markdown = mistune.create_markdown(renderer=mistune.AstRenderer())
-
-
-def get_all_ast_nodes(ast_nodes):
-    for node in ast_nodes:
-        yield node
-        if 'children' in node:
-            # workaround for https://github.com/lepture/mistune/issues/269
-            if isinstance(node['children'], str):
-                yield {'type': 'text', 'text': node['children']}
-            else:
-                yield from get_all_ast_nodes(node['children'])
-
-
-def get_text_from_ast(ast_nodes):
-    def get_text_from_node(node):
-        if node['type'] != 'text':
-            raise RuntimeError(f'unsupported node type: {node["type"]}')
-        return node['text']
-
-    return ''.join(map(get_text_from_node, ast_nodes))
-
-
 def add_page(output_root, parent, *, id=None, path=None, title=None):
     if parent.tag == 'tab':
         parent.attrib['type'] = 'usergroup'
@@ -105,13 +86,13 @@ def add_page(output_root, parent, *, id=None, path=None, title=None):
     with (OMZ_ROOT / path).open('r', encoding='utf-8') as input_file:
         lines = input_file.readlines()
 
-    ast = parse_markdown(''.join(lines))
+    page = omzdocs.DocumentationPage(''.join(lines))
 
-    if not ast or ast[0]['type'] != 'heading' or ast[0]['level'] != 1:
+    if page.title is None:
         raise RuntimeError(f'{path}: must begin with level 1 heading')
 
     if not title:
-        title = get_text_from_ast(ast[0]['children'])
+        title = page.title
 
     element.attrib['title'] = title
 
@@ -128,7 +109,7 @@ def add_page(output_root, parent, *, id=None, path=None, title=None):
         output_file.writelines(lines)
 
     # copy all referenced images
-    image_urls = [node['src'] for node in get_all_ast_nodes(ast) if node['type'] == 'image']
+    image_urls = [ref.url for ref in page.external_references() if ref.type == 'image']
 
     for image_url in image_urls:
         parsed_image_url = urllib.parse.urlparse(image_url)