Issue 7059 - Modify fldiff so it can handle multiple files

abp/filters/diff_script.py

Index: abp/filters/diff_script.py
===================================================================
--- a/abp/filters/diff_script.py
+++ b/abp/filters/diff_script.py
@@ -20,41 +20,58 @@
 import argparse
 import io
 import sys
+import os
 
 from .renderer import render_diff
+from .parser import parse_filterlist
 
 __all__ = ['main']
 
 
-def parse_args():
+class MissingFilterListError(Exception):
+    """Error in finding a latest filter list, or base filter lists."""
+
+
+def _get_version(filterlist):
+    for line in parse_filterlist(filterlist):
+        if line.type == 'header':
+            base = line.version
+        if line.type == 'metadata' and line.key == 'Version':
+            return line.value
+    raise MissingFilterListError('Unable to find Version in [{}]'.format(base))

[Vasily Kuznetsov, 2018/10/29 16:31:48]

Wouldn't it be more helpful to give filename in this error message instead of
the version from the header? What do you think?

[rhowell, 2018/10/29 20:01:40]

Yeah. With this (old) method, it returns the header line:

    Unable to find Version in [Adblock Plus 2.0]

But it does seem more accurate and explicit to return the file's name:

    Unable to find Version in
/tmp/pytest-of-emma/pytest-372/test_no_version0/root/archive/list113.txt

+
+
+def parse_args(args_in=None):
     parser = argparse.ArgumentParser(description='Render a filter list diff.')
-    parser.add_argument(
-        'base', help='the older filter list that needs to be updated',
-        nargs='?')
-    parser.add_argument(
-        'latest', help='the most recent version of the filter list',
-        nargs='?')
-    parser.add_argument(
-        'outfile', help='output file for filter list diff',
-        default='-', nargs='?')
-    return parser.parse_args()
+    parser.add_argument('latest',
+                        help='The most recent version of the filter list')
+    parser.add_argument('-o', '--output_dir', default=os.getcwd(),
+                        help='The directory to write the diffs to')
+    parser.add_argument('base_files', nargs='+',
+                        help='One or more archived filter lists')
+    return parser.parse_args(args_in)
 
 
-def main():
+def main(args_in=None):
     """Entry point for the diff rendering script (fldiff)."""
-    args = parse_args()
+    arg = parse_args(args_in)
 
-    with io.open(args.base, 'r', encoding='utf-8') as base, \
-            io.open(args.latest, 'r', encoding='utf-8') as latest:
+    with io.open(arg.latest, 'r', encoding='utf8') as latest_list:
+        latest = latest_list.readlines()
 
-        lines = render_diff(base, latest)
-        if args.outfile == '-':
-            outfile = io.open(sys.stdout.fileno(), 'w',
-                              closefd=False,
-                              encoding=sys.stdout.encoding or 'utf-8')
-        else:
-            outfile = io.open(args.outfile, 'w', encoding='utf-8')
+    for base_file in arg.base_files:
+        with io.open(base_file, 'r', encoding='utf8') as base_file:
+            base = base_file.readlines()
+            lines = render_diff(base, latest)
+            try:
+                version = _get_version(base)
+            except MissingFilterListError as exc:
+                sys.exit(exc)
 
-        with outfile:
-            for line in lines:
-                print(line, file=outfile)
+            # TODO: After removing the dict test, this .strip() can go
+            outfile = os.path.join(arg.output_dir.strip(),
+                                   'diff{}.txt'.format(version))
+
+            with io.open(outfile, 'w', encoding='utf-8') as out_fp:
+                for line in lines:
+                    out_fp.write(line + '\n')