Remove img_with_alt option entirely

README.md

@@ -76,9 +76,9 @@ p.to_dict(filter_by_type="h-entry")
 p.to_json(filter_by_type="h-entry")
 ```
 
-## Experimental Features 🧪
+## Breaking Changes in v2
 
-- Pass the optional argument `img_with_alt=True` to either the `Parser` object or to the `parse` method to enable parsing of the `alt` attribute of `<img>` tags according to [issue: image alt text is lost during parsing](https://github.com/microformats/microformats2-parsing/issues/2). By default this is `False` to be backwards compatible.
+- img alt support is now on by default
 
 ## FAQs ❓
 

mf2py/dom_helpers.py

@@ -39,7 +39,7 @@ def get_attr(el, attr, check_name=None):
         return el.get(attr)
 
 
-def get_img_src_alt(img, img_with_alt, base_url=""):
+def get_img_src_alt(img, base_url=""):
     """given a img element, returns both src and alt attributes as a list of tuples if alt exists, else returns the src as a string
     use for alt parsing with img
     """
@@ -50,7 +50,7 @@ def get_img_src_alt(img, img_with_alt, base_url=""):
     if src is not None:
         src = try_urljoin(base_url, src)
 
-        if alt is None or not img_with_alt:
+        if alt is None:
             return src
         else:
             return {"value": src, "alt": alt}

mf2py/implied_properties.py

@@ -73,12 +73,11 @@ def non_empty(val):
     return get_textContent(el, replace_img=True, img_to_src=False, base_url=base_url)
 
 
-def photo(el, img_with_alt, base_url=""):
+def photo(el, base_url=""):
     """Find an implied photo property
 
     Args:
       el (bs4.element.Tag): a DOM element
-      img_with_alt: a flag to enable experimental parsing of alt attribute with img (set by the Parser object)
       base_url (string): the base URL to use, to reconcile relative URLs
 
     Returns:
@@ -105,7 +104,7 @@ def get_photo_child(children):
                 return poss_obj
 
     # if element is an img use source if exists
-    prop_value = get_img_src_alt(el, img_with_alt, base_url)
+    prop_value = get_img_src_alt(el, base_url)
     if prop_value is not None:
         return prop_value
 
@@ -132,7 +131,7 @@ 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, img_with_alt, base_url)
+        prop_value = get_img_src_alt(poss_child, base_url)
         if prop_value is not None:
             return prop_value
 

mf2py/parse_property.py

@@ -26,12 +26,12 @@ def text(el, base_url=""):
     return prop_value
 
 
-def url(el, img_with_alt, base_url=""):
+def url(el, base_url=""):
     """Process u-* properties"""
 
     prop_value = get_attr(el, "href", check_name=("a", "area", "link"))
     if prop_value is None:
-        prop_value = get_img_src_alt(el, img_with_alt, base_url)
+        prop_value = get_img_src_alt(el, base_url)
         if prop_value is not None:
             return prop_value
     if prop_value is None:

mf2py/parser.py

@@ -12,7 +12,7 @@
 from .version import __version__
 
 
-def parse(doc=None, url=None, html_parser=None, img_with_alt=False):
+def parse(doc=None, url=None, html_parser=None):
     """
     Parse a microformats2 document or url and return a json dictionary.
 
@@ -28,7 +28,7 @@ def parse(doc=None, url=None, html_parser=None, img_with_alt=False):
 
     Return: a json dict represented the structured data in this document.
     """
-    return Parser(doc, url, html_parser, img_with_alt).to_dict()
+    return Parser(doc, url, html_parser).to_dict()
 
 
 class Parser(object):
@@ -54,7 +54,7 @@ class Parser(object):
     ua_url = "https://github.com/microformats/mf2py"
     useragent = "{0} - version {1} - {2}".format(ua_desc, __version__, ua_url)
 
-    def __init__(self, doc=None, url=None, html_parser=None, img_with_alt=True):
+    def __init__(self, doc=None, url=None, html_parser=None):
         self.__url__ = None
         self.__doc__ = None
         self._preserve_doc = False
@@ -68,7 +68,6 @@ def __init__(self, doc=None, url=None, html_parser=None, img_with_alt=True):
                 "version": __version__,
             },
         }
-        self.__img_with_alt__ = img_with_alt
 
         # use default parser if none specified
         self.__html_parser__ = html_parser or "html5lib"
@@ -194,11 +193,7 @@ def handle_microformat(
                 if "photo" not in properties and parsed_types_aggregation.isdisjoint(
                     "uh"
                 ):
-                    x = implied_properties.photo(
-                        el,
-                        self.__img_with_alt__,
-                        base_url=self.__url__,
-                    )
+                    x = implied_properties.photo(el, base_url=self.__url__)
                     if x is not None:
                         properties["photo"] = [x]
 
@@ -304,11 +299,7 @@ def parse_props(el):
 
                 # if value has not been parsed then parse it
                 if u_value is None:
-                    u_value = parse_property.url(
-                        el,
-                        self.__img_with_alt__,
-                        base_url=self.__url__,
-                    )
+                    u_value = parse_property.url(el, base_url=self.__url__)
 
                 if root_class_names:
                     prop_value.append(

test/test_parser.py

@@ -852,20 +852,15 @@ def test_whitespace_with_tags_inside_property():
     assert result["items"][0]["properties"] == {"name": ["foo bar"]}
 
 
-# experimental features tests
-
-
 def test_photo_with_alt():
-    """Confirm that alt text in img is parsed with feature flag img_with_alt under as a u-* property and implied photo"""
+    """Confirm that alt text in img is parsed as a u-* property and implied photo"""
 
-    path = "experimental/img_with_alt.html"
+    path = "img_with_alt.html"
 
-    # without flag
     result = parse_fixture(path)
 
-    # experimental img_with_alt=True
     with open(os.path.join(TEST_DIR, path)) as f:
-        exp_result = Parser(doc=f, html_parser="html5lib", img_with_alt=True).to_dict()
+        exp_result = Parser(doc=f, html_parser="html5lib").to_dict()
 
     # simple img with u-*
     assert "/photo.jpg" == result["items"][0]["properties"]["photo"][0]