Latest Threat Research:SANDWORM_MODE: Shai-Hulud-Style npm Worm Hijacks CI Workflows and Poisons AI Toolchains.Details →
mf2util
Artifacts are distributable versions of a package. It typically includes the source code and metadata
Advanced tools
mf2util - pypi Package Compare versions
| Metadata-Version: 1.1 | ||
| Name: mf2util | ||
| Version: 0.3.3 | ||
| Version: 0.4.0 | ||
| Summary: Python Microformats2 utilities, a companion to mf2py | ||
@@ -5,0 +5,0 @@ Home-page: http://indiewebcamp.com/mf2util |
+129
-46
@@ -215,3 +215,3 @@ """Utilities for interpreting mf2 data. | ||
| def find_author(parsed, source_url=None, hentry=None): | ||
| def find_author(parsed, source_url=None, hentry=None, fetch_mf2_func=None): | ||
| """Use the authorship discovery algorithm | ||
@@ -223,4 +223,19 @@ https://indiewebcamp.com/authorship to determine an h-entry's | ||
| :param str source_url: the source of the parsed document. | ||
| :param hentry dict: optional, the h-entry we're examining, if omitted, | ||
| we'll just use the first one | ||
| :param fetch_mf2_func callable: optional function that takes a URL | ||
| and returns parsed mf2 | ||
| :return: a dict containing the author's name, photo, and url | ||
| """ | ||
| def find_hentry_author(hentry): | ||
| for obj in hentry['properties'].get('author', []): | ||
| return parse_author(obj) | ||
| def find_parent_hfeed_author(hentry): | ||
| for hfeed in _find_all_entries(parsed, ['h-feed']): | ||
| # find the h-entry's parent h-feed | ||
| if hentry in hfeed.get('children', []): | ||
| for obj in hfeed['properties'].get('author', []): | ||
| return parse_author(obj) | ||
| if not hentry: | ||
@@ -231,37 +246,71 @@ hentry = find_first_entry(parsed, ['h-entry']) | ||
| for obj in hentry['properties'].get('author', []): | ||
| return parse_author(obj) | ||
| author_page = None | ||
| # try to find an author of the top-level h-feed | ||
| for hfeed in (card for card in parsed['items'] | ||
| if 'h-feed' in card.get('type', [])): | ||
| for obj in hfeed['properties'].get('author', []): | ||
| return parse_author(obj) | ||
| # 3. if the h-entry has an author property, use that | ||
| author = find_hentry_author(hentry) | ||
| # top-level h-cards | ||
| hcards = [card for card in parsed['items'] | ||
| if 'h-card' in card.get('type', [])] | ||
| # 4. otherwise if the h-entry has a parent h-feed with author property, | ||
| # use that | ||
| if not author: | ||
| author = find_parent_hfeed_author(hentry) | ||
| if source_url: | ||
| for item in hcards: | ||
| if source_url in item['properties'].get('url', []): | ||
| return parse_author(item) | ||
| # 5. if an author property was found | ||
| if author: | ||
| # 5.2 otherwise if author property is an http(s) URL, let the | ||
| # author-page have that URL | ||
| if list(author.keys()) == ['url']: | ||
| author_page = author['url'] | ||
| # 5.1 if it has an h-card, use it, exit. | ||
| # 5.3 otherwise use the author property as the author name, | ||
| # exit. | ||
| else: | ||
| return author | ||
| rel_mes = parsed.get('rels', {}).get("me", []) | ||
| for item in hcards: | ||
| urls = item['properties'].get('url', []) | ||
| if any(url in rel_mes for url in urls): | ||
| return parse_author(item) | ||
| # 6. if there is no author-page and the h-entry's page is a permalink page | ||
| if not author_page: | ||
| # 6.1 if the page has a rel-author link, let the author-page's | ||
| # URL be the href of the rel-author link | ||
| rel_authors = parsed.get('rels', {}).get('author', []) | ||
| if rel_authors: | ||
| author_page = rel_authors[0] | ||
| rel_authors = parsed.get('rels', {}).get("author", []) | ||
| for item in hcards: | ||
| urls = item['properties'].get('url', []) | ||
| if any(url in rel_authors for url in urls): | ||
| return parse_author(item) | ||
| # 7. if there is an author-page URL | ||
| if author_page: | ||
| if not fetch_mf2_func: | ||
| return {'url': author_page} | ||
| # just return the first h-card | ||
| if hcards: | ||
| return parse_author(hcards[0]) | ||
| # 7.1 get the author-page from that URL and parse it for microformats2 | ||
| parsed = fetch_mf2_func(author_page) | ||
| hcards = find_all_entries(parsed, ['h-card']) | ||
| # 7.2 if author-page has 1+ h-card with url == uid == | ||
| # author-page's URL, then use first such h-card, exit. | ||
| for hcard in hcards: | ||
| hcard_url = get_plain_text(hcard['properties'].get('url')) | ||
| hcard_uid = get_plain_text(hcard['properties'].get('uid')) | ||
| if (hcard_url and hcard_uid and hcard_url == hcard_uid | ||
| and hcard_url == author_page): | ||
| return parse_author(hcard) | ||
| # 7.3 else if author-page has 1+ h-card with url property | ||
| # which matches the href of a rel-me link on the author-page | ||
| # (perhaps the same hyperlink element as the u-url, though not | ||
| # required to be), use first such h-card, exit. | ||
| rel_mes = parsed.get('rels', {}).get('me', []) | ||
| for hcard in hcards: | ||
| hcard_url = get_plain_text(hcard['properties'].get('url')) | ||
| if hcard_url and hcard_url in rel_mes: | ||
| return parse_author(hcard) | ||
| # 7.4 if the h-entry's page has 1+ h-card with url == | ||
| # author-page URL, use first such h-card, exit. | ||
| for hcard in hcards: | ||
| hcard_url = get_plain_text(hcard['properties'].get('url')) | ||
| if hcard_url and hcard_url == author_page: | ||
| return parse_author(hcard) | ||
| # 8. otherwise no deterministic author can be found. | ||
| return None | ||
| def representative_hcard(parsed, source_url): | ||
@@ -465,3 +514,5 @@ """Find the representative h-card for a URL | ||
| def _interpret_common_properties(parsed, source_url, base_href, hentry, use_rel_syndication, want_json): | ||
| def _interpret_common_properties( | ||
| parsed, source_url, base_href, hentry, use_rel_syndication, | ||
| want_json, fetch_mf2_func): | ||
| result = {} | ||
@@ -487,3 +538,3 @@ for prop in ('url', 'uid', 'photo'): | ||
| author = find_author(parsed, source_url, hentry) | ||
| author = find_author(parsed, source_url, hentry, fetch_mf2_func) | ||
| if author: | ||
@@ -504,2 +555,9 @@ result['author'] = author | ||
| summary_prop = hentry['properties'].get('summary') | ||
| if summary_prop: | ||
| if isinstance(summary_prop[0], dict): | ||
| result['summary'] = summary_prop[0]['value'] | ||
| else: | ||
| result['summary'] = summary_prop[0] | ||
| # TODO handle h-adr and h-geo variants | ||
@@ -527,3 +585,5 @@ locations = hentry['properties'].get('location') | ||
| def interpret_event(parsed, source_url, base_href=None, hevent=None, use_rel_syndication=True, want_json=False): | ||
| def interpret_event( | ||
| parsed, source_url, base_href=None, hevent=None, | ||
| use_rel_syndication=True, want_json=False, fetch_mf2_func=None): | ||
| """Given a document containing an h-event, return a dictionary:: | ||
@@ -552,2 +612,4 @@ | ||
| will be pure json with datetimes as strings instead of python objects | ||
| :param callable fetch_mf2_func: (optional) function to fetch mf2 parsed | ||
| output for a given URL. | ||
| :return: a dict with some or all of the described properties | ||
@@ -562,3 +624,4 @@ """ | ||
| result = _interpret_common_properties( | ||
| parsed, source_url, base_href, hevent, use_rel_syndication, want_json) | ||
| parsed, source_url, base_href, hevent, use_rel_syndication, want_json, | ||
| fetch_mf2_func) | ||
| result['type'] = 'event' | ||
@@ -571,3 +634,5 @@ name_value = get_plain_text(hevent['properties'].get('name')) | ||
| def interpret_entry(parsed, source_url, base_href=None, hentry=None, use_rel_syndication=True, want_json=False): | ||
| def interpret_entry( | ||
| parsed, source_url, base_href=None, hentry=None, | ||
| use_rel_syndication=True, want_json=False, fetch_mf2_func=None): | ||
| """Given a document containing an h-entry, return a dictionary:: | ||
@@ -609,2 +674,4 @@ | ||
| will be pure json with datetimes as strings instead of python objects | ||
| :param callable fetch_mf2_func: (optional) function to fetch mf2 parsed | ||
| output for a given URL. | ||
| :return: a dict with some or all of the described properties | ||
@@ -620,3 +687,4 @@ """ | ||
| result = _interpret_common_properties( | ||
| parsed, source_url, base_href, hentry, use_rel_syndication, want_json) | ||
| parsed, source_url, base_href, hentry, use_rel_syndication, want_json, | ||
| fetch_mf2_func) | ||
| if 'h-cite' in hentry.get('type', []): | ||
@@ -636,3 +704,4 @@ result['type'] = 'cite' | ||
| result.setdefault(prop, []).append( | ||
| interpret(parsed, source_url, base_href, url_val, want_json)) | ||
| interpret(parsed, source_url, base_href, url_val, | ||
| want_json, fetch_mf2_func)) | ||
| else: | ||
@@ -646,3 +715,4 @@ result.setdefault(prop, []).append({ | ||
| def interpret_feed(parsed, source_url, base_href=None, hfeed=None): | ||
| def interpret_feed(parsed, source_url, base_href=None, hfeed=None, | ||
| fetch_mf2_func=None): | ||
| """Interpret a source page as an h-feed or as an top-level collection | ||
@@ -655,4 +725,6 @@ of h-entries. | ||
| :param str base_href: (optional) the href value of the base tag | ||
| :param dict item: (optional) the item to be parsed. If provided, | ||
| this will be used instead of the first element on the page. | ||
| :param dict hfedd: (optional) the h-feed to be parsed. If provided, | ||
| this will be used instead of the first h-feed on the page. | ||
| :param callable fetch_mf2_func: (optional) function to fetch mf2 parsed | ||
| output for a given URL. | ||
| :return: a dict containing 'entries', a list of entries, and possibly other | ||
@@ -679,3 +751,3 @@ feed properties (like 'name'). | ||
| parsed, source_url, base_href, item=child, | ||
| use_rel_syndication=False) | ||
| use_rel_syndication=False, fetch_mf2_func=fetch_mf2_func) | ||
| if entry: | ||
@@ -688,3 +760,3 @@ entries.append(entry) | ||
| def interpret(parsed, source_url, base_href=None, item=None, | ||
| use_rel_syndication=True, want_json=False): | ||
| use_rel_syndication=True, want_json=False, fetch_mf2_func=None): | ||
| """Interpret a permalink of unknown type. Finds the first interesting | ||
@@ -706,2 +778,4 @@ h-* element, and delegates to :func:`interpret_entry` if it is an | ||
| will be pure json with datetimes as strings instead of python objects | ||
| :param callable fetch_mf2_func: (optional) function to fetch mf2 parsed | ||
| output for a given URL. | ||
| :return: a dict as described by interpret_entry or interpret_event, or None | ||
@@ -713,11 +787,17 @@ """ | ||
| if item: | ||
| if 'h-event' in item.get('type', []): | ||
| types = item.get('type', []) | ||
| if 'h-event' in types: | ||
| return interpret_event( | ||
| parsed, source_url, base_href=base_href, hevent=item, use_rel_syndication=use_rel_syndication, want_json=want_json) | ||
| elif 'h-entry' in item.get('type', []) or 'h-cite' in item.get('type', []): | ||
| parsed, source_url, base_href=base_href, hevent=item, | ||
| use_rel_syndication=use_rel_syndication, want_json=want_json, | ||
| fetch_mf2_func=fetch_mf2_func) | ||
| elif 'h-entry' in types or 'h-cite' in types: | ||
| return interpret_entry( | ||
| parsed, source_url, base_href=base_href, hentry=item, use_rel_syndication=use_rel_syndication, want_json=want_json) | ||
| parsed, source_url, base_href=base_href, hentry=item, | ||
| use_rel_syndication=use_rel_syndication, want_json=want_json, | ||
| fetch_mf2_func=fetch_mf2_func) | ||
| def interpret_comment(parsed, source_url, target_urls, base_href=None, want_json=False): | ||
| def interpret_comment(parsed, source_url, target_urls, base_href=None, | ||
| want_json=False, fetch_mf2_func=None): | ||
| """Interpret received webmentions, and classify as like, reply, or | ||
@@ -741,2 +821,4 @@ repost (or a combination thereof). Returns a dict as described | ||
| will be pure json with datetimes as strings instead of python objects | ||
| :param callable fetch_mf2_func: (optional) function to fetch mf2 parsed | ||
| output for a given URL. | ||
| :return: a dict as described above, or None | ||
@@ -747,3 +829,4 @@ """ | ||
| result = interpret_entry(parsed, source_url, base_href=base_href, | ||
| hentry=item, want_json=want_json) | ||
| hentry=item, want_json=want_json, | ||
| fetch_mf2_func=fetch_mf2_func) | ||
| if result: | ||
@@ -750,0 +833,0 @@ result['comment_type'] = classify_comment(parsed, target_urls) |
+1
-1
| Metadata-Version: 1.1 | ||
| Name: mf2util | ||
| Version: 0.3.3 | ||
| Version: 0.4.0 | ||
| Summary: Python Microformats2 utilities, a companion to mf2py | ||
@@ -5,0 +5,0 @@ Home-page: http://indiewebcamp.com/mf2util |
+2
-2
@@ -27,3 +27,3 @@ #!/usr/bin/env python | ||
| setup(name='mf2util', | ||
| version='0.3.3', | ||
| version='0.4.0', | ||
| description='Python Microformats2 utilities, a companion to mf2py', | ||
@@ -55,3 +55,3 @@ long_description=""" | ||
| py_modules=['mf2util'], | ||
| tests_require=['pytest'], | ||
| tests_require=['pytest', 'mf2py'], | ||
| cmdclass={'test': PyTest}, | ||
@@ -58,0 +58,0 @@ classifiers=[ |
Alert delta unavailable
Currently unable to show alert delta for PyPI packages.
Improved metrics
- Total package byte prevSize
35636
11.32%- Lines of code
737
11.5%