hacking on sanitizing the lines now in the release file

tools/ubuntu_package_puller/release.py

@@ -6,7 +6,7 @@ import json
 from meta_release import SourceMetaRelease, MetaRelease
 
 
-RELEASE_WORD_MATCHER = r'(^\Origin\:\s|Label:\s|Suite:\s|Version:\s|Codename:\s|Date:\s|Architecture:\s|Components:\s|Description\:\s|MD5Sum:\s)'
+RELEASE_WORD_MATCHER = r'(^\Origin\:\s|Label:\s|Suite:\s|Version:\s|Codename:\s|Date:\s|Architecture:\s|Components:\s|Description:\s|MD5Sum:\s|SHA256:\s|Aquire\-By\-Hash:\s)'
 
 class Release:
     def __init__(self, distro_codename):
@@ -24,19 +24,52 @@ class Release:
 
         for d in self.meta_release:
             meta_release_obj = MetaRelease(d)
-            dist_and_release_file_url = { meta_release_obj.dist, meta_release_obj.release_file }
+            dist_and_release_file_url = { meta_release_obj.dist: meta_release_obj.release_file }
-            print(type(dist_and_release_file_url))
             meta_release_objects.append(dist_and_release_file_url)
 
         return meta_release_objects
 
+    def line_format(self, line):
+        """ Use this method for cleaning the line, especially the one with the md5
+        and shasums in them. """
+        try:
+            #cleaned_line = re.split(RELEASE_WORD_MATCHER, line)
+            cleaned_line = line
+            return cleaned_line
+        except Exception as e:
+            print('failed to clean')
+            print(e.message)
+
+    def validate_parse(self):
+        """ Use this method for validating the entire returned dictionary. make
+        sure it has the expected keys we want/expect. """
+        return 
+
+    def md5_from_line(line):
+        return 
+
+    def sha256_from_line(line):
+        return
+
     def release_file_parse(self, release_file_url):
-        """ Returns the meta_release_file parsed as a list of dicts """
+        """ Returns the parsed_release_file parsed as a list of dicts """
         with request.urlopen(f'{release_file_url}') as response:
             index_counter = 0
             lines = TextIOWrapper(response, encoding='utf-8')
+
+            cleaned_lines = []
+
+            for l in lines:
+                cleaned_line = self.line_format(l)
+                cleaned_lines.append(cleaned_line)
+                print(cleaned_line)
+
+            return cleaned_lines
+            #return parsed_release_file
+
+"""
             stripped_lines = [
-                    re.split(RELEASE_WORD_MATCHER, l.strip()) for l in
+                    re.split(RELEASE_WORD_MATCHER, l.strip()[::1]) for l in
                     lines ]
             print(stripped_lines)
             grouped_lines = [list(group) for key, group in
@@ -57,6 +90,7 @@ class Release:
                     list_of_dicts.append(d) if arr_per_group == len(d.keys()) else None 
 
             return list_of_dicts
+"""
 
 if __name__ == '__main__':
     # testing
@@ -64,10 +98,13 @@ if __name__ == '__main__':
     r = Release('focal')
     release_file_urls = r.distro_release_file_urls()
 
-    for meta_release in release_file_urls:
+    for meta_release_dict in release_file_urls:
-        print(meta_release)
+        keys = meta_release_dict.keys()
-        #keys = meta_release.keys()
+        for distro in keys:
-        #for distro in keys:
+            url = meta_release_dict[distro]
-        #    url = meta_release[distro]
+            try:
-        #    print(url)
+                results = r.release_file_parse(url)
+            except Exception as e:
+                print(e.__doc__)
+                print(e.message)