epub converter: add color conversion, update adding style tags

src/util/color_reader.py

@@ -0,0 +1,87 @@
+from webcolors import html4_hex_to_names, hex_to_rgb, rgb_to_name
+
+
+def closest_colour_rgb(requested_colour):
+    min_colours = {}
+    for key, name in html4_hex_to_names.items():
+        r_c, g_c, b_c = hex_to_rgb(key)
+        rd = (r_c - requested_colour[0]) ** 2
+        gd = (g_c - requested_colour[1]) ** 2
+        bd = (b_c - requested_colour[2]) ** 2
+        min_colours[(rd + gd + bd)] = name
+
+    return min_colours[min(min_colours.keys())]
+
+
+def get_rgb_colour_name(c):
+    try:
+        closest_name = actual_name = rgb_to_name(c, 'html4')
+    except ValueError:
+        closest_name = closest_colour_rgb(c)
+        actual_name = None
+    if actual_name:
+        return actual_name
+    else:
+        return closest_name
+
+
+def get_hex_colour_name(c):
+    try:
+        c = hex_to_rgb(c)
+    except ValueError:
+        return ''
+
+    try:
+        closest_name = actual_name = rgb_to_name(c, 'html4')
+    except ValueError:
+        closest_name = closest_colour_rgb(c)
+        actual_name = None
+    if actual_name:
+        return actual_name
+    else:
+        return closest_name
+
+
+def str2color_name(s: str):
+    if 'rgb' in s:
+        s = s.replace('rgb', '').replace('(', '').replace(')', '')
+        try:
+            rgb = [int(x) for x in s.split(',')]
+            rgb = tuple(rgb)
+        except ValueError:
+            return ''
+        if len(rgb) != 3:
+            return ''
+        name = get_rgb_colour_name(rgb)
+        return  name
+
+    elif '#' in s:
+        name = get_hex_colour_name(s)
+        return name
+
+    else:
+        return ''
+
+
+if __name__ == '__main__':
+
+    str2color_name('rgb(139, 0, 0)')
+
+    colors = [
+        (75, 0, 130), (255, 0, 255),
+        (139, 69, 19), (46, 139, 87),
+        (221, 160, 221)
+    ]
+
+    hex_colors = [
+        '#96F', '#000', '#4C4C4C', '#A00', '#99F'
+    ]
+
+    for c in colors:
+        name = get_rgb_colour_name(c)
+        print("Actual colour:", c, ", closest colour name:", name)
+
+    for c in hex_colors:
+        name = get_hex_colour_name(c)
+        print("Actual colour:", c, ", closest colour name:", name)
+        print()

src/util/css_reader.py

@@ -8,6 +8,7 @@ from itertools import takewhile
 from logging import CRITICAL
 
 from src.config import LawCartaConfig
+from src.util.color_reader import str2color_name
 
 cssutils.log.setLevel(CRITICAL)
 
@@ -75,6 +76,8 @@ LIVECARTA_STYLE_ATTRS_MAPPING = {
     'font': lambda x: '',
     'font-family': lambda x: LawCartaConfig.font_correspondence_table.get(x.capitalize()),
     'font-size': convert_font_size,
+    'color': str2color_name,
+    'background-color': str2color_name,
 }
 
 LIVECARTA_STYLE_ATTRS_SHOULD_BE_TAG = {
@@ -150,40 +153,43 @@ def add_inline_style_to_html_soup(soup1, css_text):
 
     for i in livecarta_p_ids:
         tag = soup1.find(attrs={'livecarta_id': i})
+        tag_initial_name = tag.name
         tag_with_style = soup2.find(attrs={'livecarta_id': i})
         if tag_with_style.attrs.get('style'):
             style = tag_with_style.attrs.get('style') + ';'
             to_remove = check_style_to_be_tag(style)
+            new_tags = []
 
             for i, (p, v) in enumerate(to_remove):
                 s = f'{p}:{v};'
                 style = style.replace(s, '')
                 if i == 0:
                     tag.name = LIVECARTA_STYLE_ATTRS_SHOULD_BE_TAG[(p, v)]
-                    tmp_attrs = tag.attrs.copy()
+                    new_tags.append(tag)
-                    tag.attrs = {}
-
-                    new_tag = BeautifulSoup(features='lxml').new_tag('span')
-                    new_tag.attrs = tmp_attrs
-                    tag.wrap(new_tag)
-                    print(new_tag)
                 else:
                     name = LIVECARTA_STYLE_ATTRS_SHOULD_BE_TAG[(p, v)]
                     new_tag = BeautifulSoup(features='lxml').new_tag(name)
-                    tag.wrap(new_tag)
+                    new_tags[-1].wrap(new_tag)
+                    new_tags.append(new_tag)
 
             if to_remove:
-                new_tag = BeautifulSoup(features='lxml').new_tag('span')
+                style = style.strip()
-                new_tag.attrs['style'] = style
+                tmp_attrs = tag.attrs.copy()
-                tag.wrap(new_tag)
+                tag.attrs = {}
-                print(tag)
+
-                print(list(tag.parent))
+                span_tag = BeautifulSoup(features='lxml').new_tag(tag_initial_name)
-                print()
+                span_tag.attrs = tmp_attrs
-                print('---')
+                if style:
+                    span_tag.attrs['style'] = style
+                del span_tag.attrs['livecarta_id']
+
+                new_tags[-1].wrap(span_tag)
             else:
                 tag.attrs['style'] = style
                 del tag.attrs['livecarta_id']
 
+        else:
+            del tag.attrs['livecarta_id']
     return soup1