Merge branch 'main' into handle-relative-urls-in-e

.github/workflows/tests.yml

@@ -11,7 +11,7 @@ jobs:
   build-macos:
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "pypy3.8", "pypy3.9", "pypy3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     runs-on: "macos-latest"
     steps:
       - name: Install md5sha1sum
@@ -26,7 +26,7 @@ jobs:
       - name: Install Poetry
         uses: snok/install-poetry@v1
         with:
-          version: 1.2.2
+          version: 1.5.1
           virtualenvs-in-project: true
       - name: Install dependencies
         run: poetry install --no-interaction --no-root
@@ -43,7 +43,7 @@ jobs:
   build-linux:
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "pypy3.8", "pypy3.9", "pypy3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     runs-on: "ubuntu-latest"
     steps:
       - name: Install libxml2
@@ -60,7 +60,7 @@ jobs:
       - name: Install Poetry
         uses: snok/install-poetry@v1
         with:
-          version: 1.2.2
+          version: 1.5.1
           virtualenvs-in-project: true
       - name: Install dependencies
         run: poetry install --no-interaction --no-root
@@ -77,7 +77,7 @@ jobs:
   build-windows:
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     runs-on: "windows-latest"
     defaults:
       run:
@@ -93,7 +93,7 @@ jobs:
       - name: Install Poetry
         uses: snok/install-poetry@v1
         with:
-          version: 1.2.2
+          version: 1.5.1
           virtualenvs-in-project: true
       - name: Install dependencies
         run: poetry install --no-interaction --no-root

CHANGELOG.md

@@ -22,7 +22,7 @@ All notable changes to this project will be documented in this file.
 ## 1.1.1 - 2018-06-15
 
 - streamline backcompat to use JSON only.
-- fix multiple mf1 root rel-tag parsing 
+- fix multiple mf1 root rel-tag parsing
 - correct url and photo for hreview.
 - add rules for nested hreview. update backcompat to use multiple matches in old properties.
 - fix `rel-tag` to `p-category` conversion so that other classes are not lost.
@@ -37,11 +37,11 @@ All notable changes to this project will be documented in this file.
 - better whitespace algorithm for `name` and `html.value` parsing
 - experimental flag for including `alt` in `u-photo` parsing
 - make a copy of the BeautifulSoup given by user to work on for parsing to prevent changes to original doc
-- bump version to 1.1.1 
+- bump version to 1.1.1
 
 ## 1.1.0 - 2018-03-16
 
-- bump version to 1.1.0 since it is a "major" change 
+- bump version to 1.1.0 since it is a "major" change
 - added tests for new implied name rules
 - modified earlier tests to accommodate new rules
 - use space separator instead of "T"
@@ -59,12 +59,12 @@ All notable changes to this project will be documented in this file.
 ## 1.0.6 - 2018-03-04
 
 - strip leading/trailing white space for `e-*[html]`. update the corresponding tests
-- blank values explicitly authored are allowed as property values 
+- blank values explicitly authored are allowed as property values
 - include `alt` or `src` from `<img>` in parsing for `p-*` and `e-*[value]`
-- parse `title` from `<link>` for `p-*` resolves #84 
-- and `poster` from `<video>` for `u-*` resolves #76 
+- parse `title` from `<link>` for `p-*` resolves #84
+- and `poster` from `<video>` for `u-*` resolves #76
 - use `html5lib` as default parser
-- use the final redirect URL resolves #62 
+- use the final redirect URL resolves #62
 - update requirements to use BS4 v4.6.0 and html5lib v1.0.1
 - drop support for Python 2.6 as html5lib dropped support
 

CONTRIBUTING.md

@@ -38,7 +38,7 @@ PRs must pass all tests and linting requirements before they can be merged.
 Before you submit a PR to `mf2py`, run the following command in the base directory of the project:
 
 ```bash
-make style
+make lint
 ```
 
 This will format your code using the linters configured with the project.

mf2py/datetime_helpers.py

@@ -58,5 +58,5 @@ def normalize_datetime(dtstr, match=None):
 
         tzstr = match.group("tz")
         if tzstr:
-            dtstr += tzstr
+            dtstr += tzstr.replace(":", "")
     return dtstr

mf2py/implied_properties.py

@@ -103,15 +103,20 @@ def get_photo_child(children):
             if not mf2_classes.root(poss_obj.get("class", [])):
                 return poss_obj
 
-    # if element is an img use source if exists
-    prop_value = get_img_src_alt(el, base_url)
-    if prop_value is not None:
+    def resolve_relative_url(prop_value):
+        if isinstance(prop_value, dict):
+            prop_value["value"] = try_urljoin(base_url, prop_value["value"])
+        else:
+            prop_value = try_urljoin(base_url, prop_value)
         return prop_value
 
+    # if element is an img use source if exists
+    if prop_value := get_img_src_alt(el, base_url):
+        return resolve_relative_url(prop_value)
+
     # if element is an object use data if exists
-    prop_value = get_attr(el, "data", check_name="object")
-    if prop_value is not None:
-        return prop_value
+    if prop_value := get_attr(el, "data", check_name="object"):
+        return resolve_relative_url(prop_value)
 
     # find candidate child or grandchild
     poss_child = None
@@ -131,14 +136,12 @@ def get_photo_child(children):
     # if a possible child was found parse
     if poss_child is not None:
         # img get src
-        prop_value = get_img_src_alt(poss_child, base_url)
-        if prop_value is not None:
-            return prop_value
+        if prop_value := get_img_src_alt(poss_child, base_url):
+            return resolve_relative_url(prop_value)
 
         # object get data
-        prop_value = get_attr(poss_child, "data", check_name="object")
-        if prop_value is not None:
-            return prop_value
+        if prop_value := get_attr(poss_child, "data", check_name="object"):
+            return resolve_relative_url(prop_value)
 
 
 def url(el, base_url=""):

test/examples/implied_properties/implied_photo_relative_url.html

@@ -0,0 +1,5 @@
+<html>
+<base href="http://example.com">
+<img class="h-card" alt="Jane Doe" src="jane-img.jpeg">
+<object class="h-card" data="jane-object.jpeg">Jane Doe</object>
+</html>

test/test_parser.py

@@ -136,11 +136,11 @@ def test_plain_child_microformat():
 
 def test_datetime_parsing():
     result = parse_fixture("datetimes.html")
-    assert result["items"][0]["properties"]["start"][0] == "2014-01-01T12:00:00+00:00"
-    assert result["items"][0]["properties"]["end"][0] == "3014-01-01T18:00:00+00:00"
+    assert result["items"][0]["properties"]["start"][0] == "2014-01-01T12:00:00+0000"
+    assert result["items"][0]["properties"]["end"][0] == "3014-01-01T18:00:00+0000"
     assert result["items"][0]["properties"]["duration"][0] == "P1000Y"
-    assert result["items"][0]["properties"]["updated"][0] == "2011-08-26T00:01:21+00:00"
-    assert result["items"][0]["properties"]["updated"][1] == "2011-08-26T00:01:21+00:00"
+    assert result["items"][0]["properties"]["updated"][0] == "2011-08-26T00:01:21+0000"
+    assert result["items"][0]["properties"]["updated"][1] == "2011-08-26T00:01:21+0000"
 
 
 def test_datetime_vcp_parsing():
@@ -149,19 +149,19 @@ def test_datetime_vcp_parsing():
     assert result["items"][1]["properties"]["published"][0] == "3014-01-01 01:21Z"
     assert result["items"][2]["properties"]["updated"][0] == "2014-03-11 09:55"
     assert result["items"][3]["properties"]["published"][0] == "2014-01-30 15:28"
-    assert result["items"][4]["properties"]["published"][0] == "9999-01-14T11:52+08:00"
-    assert result["items"][5]["properties"]["published"][0] == "2014-06-01 12:30-06:00"
-    assert result["items"][8]["properties"]["start"][0] == "2014-06-01 12:30-06:00"
-    assert result["items"][9]["properties"]["start"][0] == "2014-06-01 12:30-06:00"
-    assert result["items"][10]["properties"]["start"][0] == "2014-06-01 00:30-06:00"
+    assert result["items"][4]["properties"]["published"][0] == "9999-01-14T11:52+0800"
+    assert result["items"][5]["properties"]["published"][0] == "2014-06-01 12:30-0600"
+    assert result["items"][8]["properties"]["start"][0] == "2014-06-01 12:30-0600"
+    assert result["items"][9]["properties"]["start"][0] == "2014-06-01 12:30-0600"
+    assert result["items"][10]["properties"]["start"][0] == "2014-06-01 00:30-0600"
     assert result["items"][10]["properties"]["end"][0] == "2014-06-01 12:15"
-    assert result["items"][10]["properties"]["start"][1] == "2014-06-01 00:30-06:00"
+    assert result["items"][10]["properties"]["start"][1] == "2014-06-01 00:30-0600"
     assert result["items"][10]["properties"]["end"][1] == "2014-06-01 12:15"
-    assert result["items"][11]["properties"]["start"][0] == "2016-03-02 00:30-06:00"
-    assert result["items"][12]["properties"]["start"][0] == "2014-06-01 12:30-6:00"
-    assert result["items"][13]["properties"]["start"][0] == "2014-06-01 12:30+6:00"
+    assert result["items"][11]["properties"]["start"][0] == "2016-03-02 00:30-0600"
+    assert result["items"][12]["properties"]["start"][0] == "2014-06-01 12:30-600"
+    assert result["items"][13]["properties"]["start"][0] == "2014-06-01 12:30+600"
     assert result["items"][14]["properties"]["start"][0] == "2014-06-01 12:30Z"
-    assert result["items"][15]["properties"]["start"][0] == "2014-06-01 12:30-6:00"
+    assert result["items"][15]["properties"]["start"][0] == "2014-06-01 12:30-600"
 
 
 def test_dt_end_implied_date():
@@ -175,8 +175,8 @@ def test_dt_end_implied_date():
     assert event_wo_tz["properties"]["end"][0] == "2014-05-21 19:30"
 
     event_w_tz = result["items"][7]
-    assert event_w_tz["properties"]["start"][0] == "2014-06-01 12:30-06:00"
-    assert event_w_tz["properties"]["end"][0] == "2014-06-01 19:30-06:00"
+    assert event_w_tz["properties"]["start"][0] == "2014-06-01 12:30-0600"
+    assert event_w_tz["properties"]["end"][0] == "2014-06-01 19:30-0600"
 
 
 def test_embedded_parsing():
@@ -465,6 +465,17 @@ def test_implied_photo():
     for i in range(12, 23):
         assert "photo" not in result["items"][i]["properties"]
 
+    result = parse_fixture("implied_properties/implied_photo_relative_url.html")
+
+    assert (
+        result["items"][0]["properties"]["photo"][0]["value"]
+        == "http://example.com/jane-img.jpeg"
+    )
+    assert (
+        result["items"][1]["properties"]["photo"][0]
+        == "http://example.com/jane-object.jpeg"
+    )
+
 
 def test_implied_url():
     result = parse_fixture("implied_properties/implied_url.html")