updated syntax using Black

Author: TimidRobot

tools/prep_cc4_code.py

@@ -17,35 +17,48 @@
 import re, sys, re, getopt
 from pathlib import Path
 
+
 class UpdateLicenseCode(object):
     """One time script modifying 4.0 legal code files for updated look. This does not change
        legal code language. It adds a header and footer placeholders, and updates the HTML head.
        This allows the update_cc4_code.py script to function."""
 
-    placeholders = {\
-        'head': ('<!-- Head Start - DO NOT DELETE -->', '<!-- Head End - DO NOT DELETE -->'), \
-        'header': ('<!-- Site Header Start - DO NOT DELETE -->', '<!-- Site Header End - DO NOT DELETE -->'), \
-        'footer': ('<!-- Site Footer Start - DO NOT DELETE -->', '<!-- Site Footer End - DO NOT DELETE -->'), \
-        'language-selector': ('<!-- Language Selector Start - DO NOT DELETE -->', '<!-- Language Selector End - DO NOT DELETE -->') \
+    placeholders = {
+        "head": (
+            "<!-- Head Start - DO NOT DELETE -->",
+            "<!-- Head End - DO NOT DELETE -->",
+        ),
+        "header": (
+            "<!-- Site Header Start - DO NOT DELETE -->",
+            "<!-- Site Header End - DO NOT DELETE -->",
+        ),
+        "footer": (
+            "<!-- Site Footer Start - DO NOT DELETE -->",
+            "<!-- Site Footer End - DO NOT DELETE -->",
+        ),
+        "language-selector": (
+            "<!-- Language Selector Start - DO NOT DELETE -->",
+            "<!-- Language Selector End - DO NOT DELETE -->",
+        ),
     }
 
     image_map = {
-        'by': {'file': 'attribution_icon_white.svg', 'alt_text': 'Attribution'},
-        'sa': {'file': 'sa_white.svg', 'alt_text': 'Share Alike'},
-        'nd': {'file': 'nd_white.svg', 'alt_text': 'No Derivatives'},
-        'nc': {'file': 'nc_white.svg', 'alt_text': 'Non-Commerical'}
+        "by": {"file": "attribution_icon_white.svg", "alt_text": "Attribution"},
+        "sa": {"file": "sa_white.svg", "alt_text": "Share Alike"},
+        "nd": {"file": "nd_white.svg", "alt_text": "No Derivatives"},
+        "nc": {"file": "nc_white.svg", "alt_text": "Non-Commerical"},
     }
 
     def usage(self):
-        print('')
-        print('prep_cc4_code.py [-v]')
-        print('  -v: Verbose output')
-        print('')
-        print('  e.g. prep_cc4_code.py')
-        print('       prep_cc4_code.py -v')
-
-    def log(self, message, type = 'standard'):
-        if (type == 'standard') or (type == 'verbose' and self.verbose):
+        print("")
+        print("prep_cc4_code.py [-v]")
+        print("  -v: Verbose output")
+        print("")
+        print("  e.g. prep_cc4_code.py")
+        print("       prep_cc4_code.py -v")
+
+    def log(self, message, type="standard"):
+        if (type == "standard") or (type == "verbose" and self.verbose):
             print(message)
 
     def get_args(self):
@@ -60,9 +73,9 @@ def get_args(self):
         self.verbose = False
         self.add_placeholders = False
         for option in opts:
-            if '-v' in option:
+            if "-v" in option:
                 self.verbose = True
-            elif '-a' in option:
+            elif "-a" in option:
                 self.add_placeholders = True
 
         return True
@@ -72,16 +85,16 @@ def get_path(self):
         self.path = False
         path = Path.cwd()
         pathdir = path.name
-        if pathdir == 'legalcode':
+        if pathdir == "legalcode":
             self.path = path
-        if pathdir == 'docroot':
-            self.path = path / 'legalcode'
-        if pathdir == 'tools':
-            self.path = path.parent / 'docroot' /'legalcode'
+        if pathdir == "docroot":
+            self.path = path / "legalcode"
+        if pathdir == "tools":
+            self.path = path.parent / "docroot" / "legalcode"
         if not self.path:
-            print('Please run from within the checked-out project.')
+            print("Please run from within the checked-out project.")
         if self.path:
-            self.includes_path = self.path / 'includes'
+            self.includes_path = self.path / "includes"
         return self.path != False
 
     def process_files(self, filelist):
@@ -95,45 +108,48 @@ def process_file(self, filepath):
            - Remove references to deed3 css files
            - Remove inline styles
            - Remove Creative Commons text header"""
-        self.log('Processing: ' + filepath.name, 'verbose')
-        with filepath.open(encoding='utf-8') as infile:
+        self.log("Processing: " + filepath.name, "verbose")
+        with filepath.open(encoding="utf-8") as infile:
             content = infile.read()
         license_attrs = self.get_license_attrs(filepath.name)
-            
+
         content = self.handle_placeholders(content)
         content = self.remove_deed3_css(content)
         content = self.handle_rtl_css(content)
         content = self.remove_old_text_header(content)
         content = self.remove_inline_styles(content)
         content = self.remove_unported_image(content)
-        content = self.add_language_class(content, license_attrs['language'])
-        content = self.add_type_logos(content, license_attrs['type'])
+        content = self.add_language_class(content, license_attrs["language"])
+        content = self.add_type_logos(content, license_attrs["type"])
         content = self.handling_consideration_blockquotes(content)
 
-        self.log('   Updating content: ' + filepath.name, 'verbose')
-        with filepath.open('w', encoding='utf-8') as outfile:
+        self.log("   Updating content: " + filepath.name, "verbose")
+        with filepath.open("w", encoding="utf-8") as outfile:
             outfile.write(content)
 
     def handle_placeholders(self, content):
-        self.log('   Adding placeholders', 'verbose')
+        self.log("   Adding placeholders", "verbose")
         # The language selector has to come after the header. Because dictionaries don't
         # maint order the easiest way to maintain order is sorting the interation keys.
         for placeholder_pair in sorted(UpdateLicenseCode.placeholders):
             if self.has_placeholders(content, placeholder_pair):
-                self.log('   Found placeholder: ' + placeholder_pair + ', skipping', 'verbose')
+                self.log(
+                    "   Found placeholder: " + placeholder_pair + ", skipping",
+                    "verbose",
+                )
             else:
                 start, end = UpdateLicenseCode.placeholders[placeholder_pair]
-                if placeholder_pair == 'head':
-                    target = '</head>'
+                if placeholder_pair == "head":
+                    target = "</head>"
                     replacement = start + "\n" + end + "\n" + target
-                elif placeholder_pair == 'header':
-                    target = re.search('<body.*?>', content).group()
+                elif placeholder_pair == "header":
+                    target = re.search("<body.*?>", content).group()
                     replacement = target + "\n" + start + "\n" + end
-                elif placeholder_pair == 'footer':
-                    target = '</body>'
+                elif placeholder_pair == "footer":
+                    target = "</body>"
                     replacement = start + "\n" + end + "\n" + target
-                elif placeholder_pair == 'language-selector':
-                    target = '<!-- Site Header End - DO NOT DELETE -->'
+                elif placeholder_pair == "language-selector":
+                    target = "<!-- Site Header End - DO NOT DELETE -->"
                     replacement = target + "\n" + start + "\n" + end
                 content = content.replace(target, replacement, 1)
         return content
@@ -148,94 +164,107 @@ def has_placeholders(self, content, pair_name):
 
     def remove_deed3_css(self, content):
         """Remove refererences to deed3 css stylesheets from HEAD"""
-        self.log('   Removing deed3 css references from head', 'verbose')
+        self.log("   Removing deed3 css references from head", "verbose")
         content = re.sub(r"\n.*?<link.*?deed3\.css.*?>.*?\n", "\n", content)
         content = re.sub(r"\n.*?<link.*?deed3\-print\.css.*?>.*?\n", "\n", content)
         content = re.sub(r"\n.*?<link.*?deed3\-ie\.css.*?>.*?\n", "\n", content)
         return content
-    
+
     def handle_rtl_css(self, content):
         """The Right-to-Left stylesheet needs to come after the HEAD includes
             and be renamed"""
-        self.log('   Handling right to left css', 'verbose')
-        if content.find('deed3-rtl.css') != -1:
+        self.log("   Handling right to left css", "verbose")
+        if content.find("deed3-rtl.css") != -1:
             content = re.sub(r"\n.*?<link.*?deed3\-rtl\.css.*?>.*?\n", "\n", content)
-            bottom_placholder = UpdateLicenseCode.placeholders['head'][1]
+            bottom_placholder = UpdateLicenseCode.placeholders["head"][1]
             new_rtl_css = '<link rel="stylesheet" type="text/css" href="/includes/legalcode-rtl.css" media="all">'
-            content = content.replace(bottom_placholder, bottom_placholder + '\n' + new_rtl_css)
+            content = content.replace(
+                bottom_placholder, bottom_placholder + "\n" + new_rtl_css
+            )
         return content
 
     def remove_old_text_header(self, content):
         """Remove the paragraph string with id=header"""
-        self.log('   Removing paragraph with id="header"', 'verbose')
+        self.log('   Removing paragraph with id="header"', "verbose")
         content = re.sub(r'<p.*?id="header".*?</p>', "", content, 0, re.DOTALL)
         return content
 
     def remove_inline_styles(self, content):
         """Remove inline styles"""
-        self.log('   Remove inline styles', 'verbose')
-        content = re.sub(r'<style.*?</style>', "", content, 0, re.DOTALL)
+        self.log("   Remove inline styles", "verbose")
+        content = re.sub(r"<style.*?</style>", "", content, 0, re.DOTALL)
         return content
 
     def remove_unported_image(self, content):
         """Remove inline styles"""
-        self.log('   Remove unported image', 'verbose')
-        content = re.sub(r'<img.*?src=.*?unported\.png.*?>', "", content)
+        self.log("   Remove unported image", "verbose")
+        content = re.sub(r"<img.*?src=.*?unported\.png.*?>", "", content)
         return content
 
     def add_language_class(self, content, language_code):
         """Add language class to body tag"""
-        self.log('   Add language class to body tag', 'verbose')
+        self.log("   Add language class to body tag", "verbose")
         if not language_code:
-            language_code = 'en'
-        language_class = 'lang-' + language_code
-        body_tag = re.search('<body.*?>', content, re.IGNORECASE).group()
+            language_code = "en"
+        language_class = "lang-" + language_code
+        body_tag = re.search("<body.*?>", content, re.IGNORECASE).group()
         if body_tag.find(language_class) == -1:
             # If language class not on body, add it
-            if body_tag.find('class') > 0:
+            if body_tag.find("class") > 0:
                 existing_classes = re.search('class="(.*?)"', body_tag).group(1)
-                new_body_tag = '<body class="' + existing_classes + ' ' + language_class + '">'
+                new_body_tag = (
+                    '<body class="' + existing_classes + " " + language_class + '">'
+                )
             else:
                 new_body_tag = '<body class="' + language_class + '">'
             content = content.replace(body_tag, new_body_tag)
         return content
 
     def get_license_attrs(self, filename):
-        parts    = filename.replace('.html', '').split('_')
+        parts = filename.replace(".html", "").split("_")
         lic_type = parts[0]
-        version  = parts[1]
-        language = ''
+        version = parts[1]
+        language = ""
         if len(parts) == 3:
             language = parts[2]
-        return {'language': language, 'version': version, 'type': lic_type}
+        return {"language": language, "version": version, "type": lic_type}
 
     def add_type_logos(self, content, lic_type):
-        lic_type_attrs = lic_type.split('-')
-        lic_images = ''
+        lic_type_attrs = lic_type.split("-")
+        lic_images = ""
         for lic_attr in lic_type_attrs:
-            filename = UpdateLicenseCode.image_map[lic_attr]['file']
-            alt_text = UpdateLicenseCode.image_map[lic_attr]['alt_text']
-            image_tag = '<img src="/images/deed/svg/' + filename + '" alt="' + alt_text + '"/>'
-            lic_images += '<span class="cc-icon-' + lic_attr + '">' + image_tag + '</span>'
-        cc_logo_section = re.search('<div id="cc-logo">.*?</div>', content, re.DOTALL).group()
-        new_cc_logo_section = '<div id="cc-logo">' \
-                              + '<span class="cc-icon-logo"><img src="/images/deed/svg/cc_white.svg" alt="CC"/></span>' \
-                              + lic_images \
-                              + '</div>'
+            filename = UpdateLicenseCode.image_map[lic_attr]["file"]
+            alt_text = UpdateLicenseCode.image_map[lic_attr]["alt_text"]
+            image_tag = (
+                '<img src="/images/deed/svg/' + filename + '" alt="' + alt_text + '"/>'
+            )
+            lic_images += (
+                '<span class="cc-icon-' + lic_attr + '">' + image_tag + "</span>"
+            )
+        cc_logo_section = re.search(
+            '<div id="cc-logo">.*?</div>', content, re.DOTALL
+        ).group()
+        new_cc_logo_section = (
+            '<div id="cc-logo">'
+            + '<span class="cc-icon-logo"><img src="/images/deed/svg/cc_white.svg" alt="CC"/></span>'
+            + lic_images
+            + "</div>"
+        )
         content = content.replace(cc_logo_section, new_cc_logo_section)
         return content
 
     def handling_consideration_blockquotes(self, content):
-        content = content.replace('<blockquote>', '<p class="usage-considerations">')
-        content = content.replace('</blockquote>', '</p>')
+        content = content.replace("<blockquote>", '<p class="usage-considerations">')
+        content = content.replace("</blockquote>", "</p>")
         return content
 
     def main(self):
         """Get the command line arguments, find the files, and process them"""
         if self.get_args() and self.get_path():
-            file_list = [f for f in self.path.glob('*4.0*.html')]
+            file_list = [f for f in self.path.glob("*4.0*.html")]
             self.process_files(file_list)
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     updater = UpdateLicenseCode()
     updater.main()