filter-repo (python3): replace strings with bytestrings

This is by far the largest python3 change; it consists basically of
  * using b'<str>' instead of '<str>' in lots of places
  * adding a .encode() if we really do work with a string but need to
    get it converted to a bytestring
  * replace uses of .format() with interpolation via the '%' operator,
    since bytestrings don't have a .format() method.

Signed-off-by: Elijah Newren <newren@gmail.com>

t/t9390-filter-repo.sh

@@ -450,15 +450,15 @@ test_expect_success C_LOCALE_OUTPUT '--analyze' '
 		head -n 9 README >actual &&
 		test_cmp expect actual &&
 
-		cat | tr Q "\047" >expect <<-\EOF &&
+		cat >expect <<-\EOF &&
 		=== Files by sha and associated pathnames in reverse size ===
 		Format: sha, unpacked size, packed size, filename(s) object stored as
 		  a89c82a2d4b713a125a4323d25adda062cc0013d         44         48 numbers/medium.num
 		  f00c965d8307308469e537302baa73048488f162         21         37 numbers/small.num
 		  2aa69a2a708eed00cb390e30f6bcc3eed773f390         20         36 whatever
-		  51b95456de9274c9a95f756742808dfd480b9b35         13         29 [QcapriciousQ, QfickleQ, QmercurialQ]
+		  51b95456de9274c9a95f756742808dfd480b9b35         13         29 [capricious, fickle, mercurial]
-		  732c85a1b3d7ce40ec8f78fd9ffea32e9f45fae0          5         20 [Qsequence/knowQ, Qwords/knowQ]
+		  732c85a1b3d7ce40ec8f78fd9ffea32e9f45fae0          5         20 [sequence/know, words/know]
-		  34b6a0c9d02cb6ef7f409f248c0c1224ce9dd373          5         20 [Qsequence/toQ, Qwords/toQ]
+		  34b6a0c9d02cb6ef7f409f248c0c1224ce9dd373          5         20 [sequence/to, words/to]
 		  7ecb56eb3fa3fa6f19dd48bca9f971950b119ede          3         18 words/know
 		EOF
 		test_cmp expect blob-shas-and-paths.txt &&
@@ -795,7 +795,7 @@ test_expect_success 'incremental import' '
 
 		original=$(git rev-parse master) &&
 		git fast-export --reference-excluded-parents master~2..master \
-			| git filter-repo --stdin --refname-callback "return \"develop\"" &&
+			| git filter-repo --stdin --refname-callback "return b\"develop\"" &&
 		test "$(git rev-parse develop)" = "$original"
 	)
 '

t/t9391/commit_info.py

@@ -13,12 +13,12 @@ import git_filter_repo as fr
 
 def change_up_them_commits(commit):
   # Change the commit author
-  if commit.author_name == "Copy N. Paste":
+  if commit.author_name == b"Copy N. Paste":
-    commit.author_name = "Ima L. Oser"
+    commit.author_name = b"Ima L. Oser"
-    commit.author_email = "aloser@my.corp"
+    commit.author_email = b"aloser@my.corp"
 
   # Fix the author email
-  commit.author_email = re.sub("@my.crp", "@my.corp", commit.author_email)
+  commit.author_email = re.sub(b"@my.crp", b"@my.corp", commit.author_email)
 
   # Fix the committer date (bad timezone conversion in initial import)
   oldtime = fr.string_to_date(commit.committer_date)
@@ -26,7 +26,7 @@ def change_up_them_commits(commit):
   commit.committer_date = fr.date_to_string(newtime)
 
   # Fix the commit message
-  commit.message = re.sub("Marketing is staffed with pansies", "",
+  commit.message = re.sub(b"Marketing is staffed with pansies", b"",
                           commit.message)
 
 args = fr.FilteringOptions.parse_args(['--force'])

t/t9391/create_fast_export_output.py

@@ -23,82 +23,82 @@ out.importer_only()
 
 output = out._output
 
-world = Blob("Hello")
+world = Blob(b"Hello")
 world.dump(output)
 
-bar = Blob("foo\n")
+bar = Blob(b"foo\n")
 bar.dump(output)
 
-master = Reset("refs/heads/master")
+master = Reset(b"refs/heads/master")
 master.dump(output)
 
-changes = [FileChanges('M', 'world', world.id, mode="100644"),
+changes = [FileChanges(b'M', b'world', world.id, mode=b"100644"),
-           FileChanges('M', 'bar',   bar.id,   mode="100644")]
+           FileChanges(b'M', b'bar',   bar.id,   mode=b"100644")]
 when = datetime(year=2005, month=4, day=7,
                 hour=15, minute=16, second=10,
-                tzinfo=FixedTimeZone("-0700"))
+                tzinfo=FixedTimeZone(b"-0700"))
 when_string = fr.date_to_string(when)
-commit1 = Commit("refs/heads/master",
+commit1 = Commit(b"refs/heads/master",
-                 "A U Thor", "au@thor.email", when_string,
+                 b"A U Thor", b"au@thor.email", when_string,
-                 "Com M. Iter", "comm@iter.email", when_string,
+                 b"Com M. Iter", b"comm@iter.email", when_string,
-                 "My first commit!  Wooot!\n\nLonger description",
+                 b"My first commit!  Wooot!\n\nLonger description",
                  changes,
                  parents = [])
 commit1.dump(output)
 
-world = Blob("Hello\nHi")
+world = Blob(b"Hello\nHi")
 world.dump(output)
-world_link = Blob("world")
+world_link = Blob(b"world")
 world_link.dump(output)
 
-changes = [FileChanges('M', 'world',  world.id,      mode="100644"),
+changes = [FileChanges(b'M', b'world',  world.id,      mode=b"100644"),
-           FileChanges('M', 'planet', world_link.id, mode="120000")]
+           FileChanges(b'M', b'planet', world_link.id, mode=b"120000")]
 when += timedelta(days=3, hours=4, minutes=6)
 when_string = fr.date_to_string(when)
-commit2 = Commit("refs/heads/master",
+commit2 = Commit(b"refs/heads/master",
-                 "A U Thor", "au@thor.email", when_string,
+                 b"A U Thor", b"au@thor.email", when_string,
-                 "Com M. Iter", "comm@iter.email", when_string,
+                 b"Com M. Iter", b"comm@iter.email", when_string,
-                 "Make a symlink to world called planet, modify world",
+                 b"Make a symlink to world called planet, modify world",
                  changes,
                  parents = [commit1.id])
 commit2.dump(output)
 
-script = Blob("#!/bin/sh\n\necho Hello")
+script = Blob(b"#!/bin/sh\n\necho Hello")
 script.dump(output)
-changes = [FileChanges('M', 'runme', script.id, mode="100755"),
+changes = [FileChanges(b'M', b'runme', script.id, mode=b"100755"),
-           FileChanges('D', 'bar')]
+           FileChanges(b'D', b'bar')]
-when_string = "1234567890 -0700"
+when_string = b"1234567890 -0700"
-commit3 = Commit("refs/heads/master",
+commit3 = Commit(b"refs/heads/master",
-                 "A U Thor", "au@thor.email", when_string,
+                 b"A U Thor", b"au@thor.email", when_string,
-                 "Com M. Iter", "comm@iter.email", when_string,
+                 b"Com M. Iter", b"comm@iter.email", when_string,
-                 "Add runme script, remove bar",
+                 b"Add runme script, remove bar",
                  changes,
                  parents = [commit2.id])
 commit3.dump(output)
 
-progress = Progress("Done with the master branch now...")
+progress = Progress(b"Done with the master branch now...")
 progress.dump(output)
 checkpoint = Checkpoint()
 checkpoint.dump(output)
 
-devel = Reset("refs/heads/devel", commit1.id)
+devel = Reset(b"refs/heads/devel", commit1.id)
 devel.dump(output)
 
-world = Blob("Hello\nGoodbye")
+world = Blob(b"Hello\nGoodbye")
 world.dump(output)
 
-changes = [FileChanges('M', 'world', world.id, mode="100644")]
+changes = [FileChanges(b'M', b'world', world.id, mode=b"100644")]
-when = datetime(2006, 8, 17, tzinfo=FixedTimeZone("+0200"))
+when = datetime(2006, 8, 17, tzinfo=FixedTimeZone(b"+0200"))
 when_string = fr.date_to_string(when)
-commit4 = Commit("refs/heads/devel",
+commit4 = Commit(b"refs/heads/devel",
-                 "A U Thor", "au@thor.email", when_string,
+                 b"A U Thor", b"au@thor.email", when_string,
-                 "Com M. Iter", "comm@iter.email", when_string,
+                 b"Com M. Iter", b"comm@iter.email", when_string,
-                 "Modify world",
+                 b"Modify world",
                  changes,
                  parents = [commit1.id])
 commit4.dump(output)
 
-world = Blob("Hello\nHi\nGoodbye")
+world = Blob(b"Hello\nHi\nGoodbye")
 world.dump(output)
 when = fr.string_to_date(commit3.author_date) + timedelta(days=47)
 when_string = fr.date_to_string(when)
@@ -106,22 +106,22 @@ when_string = fr.date_to_string(when)
 # to the first parent.  Thus, despite the fact that runme and planet have
 # not changed and bar was not modified in the devel side, we have to list them
 # all anyway.
-changes = [FileChanges('M', 'world', world.id, mode="100644"),
+changes = [FileChanges(b'M', b'world', world.id, mode=b"100644"),
-           FileChanges('D', 'bar'),
+           FileChanges(b'D', b'bar'),
-           FileChanges('M', 'runme', script.id, mode="100755"),
+           FileChanges(b'M', b'runme', script.id, mode=b"100755"),
-           FileChanges('M', 'planet', world_link.id, mode="120000")]
+           FileChanges(b'M', b'planet', world_link.id, mode=b"120000")]
 
-commit5 = Commit("refs/heads/devel",
+commit5 = Commit(b"refs/heads/devel",
-                 "A U Thor", "au@thor.email", when_string,
+                 b"A U Thor", b"au@thor.email", when_string,
-                 "Com M. Iter", "comm@iter.email", when_string,
+                 b"Com M. Iter", b"comm@iter.email", when_string,
-                 "Merge branch 'master'\n",
+                 b"Merge branch 'master'\n",
                  changes,
                  parents = [commit4.id, commit3.id])
 commit5.dump(output)
 
 
-mytag = Tag("refs/tags/v1.0", commit5.id,
+mytag = Tag(b"refs/tags/v1.0", commit5.id,
-            "His R. Highness", "royalty@my.kingdom", when_string,
+            b"His R. Highness", b"royalty@my.kingdom", when_string,
-            "I bequeath to my peons this royal software")
+            b"I bequeath to my peons this royal software")
 mytag.dump(output)
 out.finish()

t/t9391/file_filter.py

@@ -15,14 +15,14 @@ import sys
 import git_filter_repo as fr
 
 def drop_file_by_contents(blob):
-  bad_file_contents = 'The launch code is 1-2-3-4.'
+  bad_file_contents = b'The launch code is 1-2-3-4.'
   if blob.data == bad_file_contents:
     blob.skip()
 
 def drop_files_by_name(commit):
   new_file_changes = []
   for change in commit.file_changes:
-    if not change.filename.endswith('.doc'):
+    if not change.filename.endswith(b'.doc'):
       new_file_changes.append(change)
   commit.file_changes = new_file_changes
 

t/t9391/rename-master-to-develop.py

@@ -14,8 +14,8 @@ not try to handle any such special cases.
 import git_filter_repo as fr
 
 def my_commit_callback(commit):
-  if commit.branch == "refs/heads/master":
+  if commit.branch == b"refs/heads/master":
-    commit.branch = "refs/heads/develop"
+    commit.branch = b"refs/heads/develop"
 
 args = fr.FilteringOptions.default_options()
 args.force = True

t/t9391/splice_repos.py

@@ -29,11 +29,11 @@ class InterleaveRepositories:
 
   def hold_commit(self, commit):
     commit.skip(new_id = commit.id)
-    letter = re.match('Commit (.)', commit.message).group(1)
+    letter = re.match(b'Commit (.)', commit.message).group(1)
     self.commit_map[letter] = commit
 
   def weave_commit(self, commit):
-    letter = re.match('Commit (.)', commit.message).group(1)
+    letter = re.match(b'Commit (.)', commit.message).group(1)
     prev_letter = bytes([ord(letter)-1])
 
     # Splice in any extra commits needed
@@ -53,10 +53,10 @@ class InterleaveRepositories:
       fr.record_id_rename(new_commit.id, commit.id)
 
   def run(self):
-    blob = fr.Blob('public gpg key contents')
+    blob = fr.Blob(b'public gpg key contents')
-    tag = fr.Tag('gpg-pubkey', blob.id,
+    tag = fr.Tag(b'gpg-pubkey', blob.id,
-                 'Ima Tagger', 'ima@tagg.er', '1136199845 +0300',
+                 b'Ima Tagger', b'ima@tagg.er', b'1136199845 +0300',
-                 'Very important explanation and stuff')
+                 b'Very important explanation and stuff')
 
     args = fr.FilteringOptions.parse_args(['--target', self.output_dir])
     out = fr.RepoFilter(args)

t/t9391/strip-cvs-keywords.py

@@ -18,8 +18,8 @@ def strip_cvs_keywords(blob):
   # FIXME: Should first check if blob is a text file to avoid ruining
   # binaries.  Could use python.magic here, or just output blob.data to
   # the unix 'file' command
-  pattern = r'\$(Id|Date|Source|Header|CVSHeader|Author|Revision):.*\$'
+  pattern = br'\$(Id|Date|Source|Header|CVSHeader|Author|Revision):.*\$'
-  replacement = r'$\1$'
+  replacement = br'$\1$'
   blob.data = re.sub(pattern, replacement, blob.data)
 
 args = fr.FilteringOptions.parse_args(['--force'])

t/t9391/unusual.py

@@ -21,7 +21,7 @@ import textwrap
 import git_filter_repo as fr
 
 def handle_progress(progress):
-  print("Decipher this: "+bytes(reversed(progress.message)))
+  print(b"Decipher this: "+bytes(reversed(progress.message)))
 
 def handle_checkpoint(checkpoint_object):
   # Flip a coin; see if we want to pass the checkpoint through.
@@ -44,8 +44,8 @@ def track_everything(obj):
     # projects, I'm just verifying an invariant of the current code.
     assert fr._IDS._reverse_translation[obj.id] == [obj.id - 1]
 
-mystr = 'This is the contents of the blob'
+mystr = b'This is the contents of the blob'
-compare = "Blob:\n  blob\n  mark :1\n  data {}\n  {}".format(len(mystr), mystr)
+compare = b"Blob:\n  blob\n  mark :1\n  data %d\n  %s" % (len(mystr), mystr)
 # Next line's only purpose is testing code coverage of something that helps
 # debugging git-filter-repo; it is NOT something external folks should depend
 # upon.
@@ -102,14 +102,14 @@ stream = io.BytesIO(textwrap.dedent('''
   from :3
   M 100644 :1 salutation
 
-  '''[1:]))
+  '''[1:]).encode())
 
 counts = collections.Counter()
 def look_for_reset(obj):
   print("Processing {}".format(obj))
   counts[type(obj)] += 1
   if type(obj) == fr.Reset:
-    assert obj.ref == 'refs/heads/B'
+    assert obj.ref == b'refs/heads/B'
 
 # Use all kinds of internals that external scripts should NOT use and which
 # are likely to break in the future, just to verify a few invariants...

t/t9392-python-callback.sh

@@ -51,7 +51,7 @@ test_expect_success '--filename-callback' '
 	setup filename-callback &&
 	(
 		cd filename-callback &&
-		git filter-repo --filename-callback "return None if filename.endswith(\".doc\") else \"src/\"+filename" &&
+		git filter-repo --filename-callback "return None if filename.endswith(b\".doc\") else b\"src/\"+filename" &&
 		git log --format=%n --name-only | sort | uniq | grep -v ^$ > f &&
 		! grep file.doc f &&
 		COMPARE=$(wc -l <f) &&
@@ -64,7 +64,7 @@ test_expect_success '--message-callback' '
 	setup message-callback &&
 	(
 		cd message-callback &&
-		git filter-repo --message-callback "return \"TLDR: \"+message[0:5]" &&
+		git filter-repo --message-callback "return b\"TLDR: \"+message[0:5]" &&
 		git log --format=%s >log-messages &&
 		grep TLDR:...... log-messages >modified-messages &&
 		test_line_count = 6 modified-messages
@@ -75,7 +75,7 @@ test_expect_success '--name-callback' '
 	setup name-callback &&
 	(
 		cd name-callback &&
-		git filter-repo --name-callback "return name.replace(\"N.\", \"And\")" &&
+		git filter-repo --name-callback "return name.replace(b\"N.\", b\"And\")" &&
 		git log --format=%an >log-person-names &&
 		grep Copy.And.Paste log-person-names
 	)
@@ -85,7 +85,7 @@ test_expect_success '--email-callback' '
 	setup email-callback &&
 	(
 		cd email-callback &&
-		git filter-repo --email-callback "return email.replace(\".com\", \".org\")" &&
+		git filter-repo --email-callback "return email.replace(b\".com\", b\".org\")" &&
 		git log --format=%ae%n%ce >log-emails &&
 		! grep .com log-emails &&
 		grep .org log-emails
@@ -98,7 +98,7 @@ test_expect_success '--refname-callback' '
 		cd refname-callback &&
 		git filter-repo --refname-callback "
                     dir,path = os.path.split(refname)
-                    return dir+\"/prefix-\"+path" &&
+                    return dir+b\"/prefix-\"+path" &&
 		git show-ref | grep refs/heads/prefix-master &&
 		git show-ref | grep refs/tags/prefix-v1.0 &&
 		git show-ref | grep refs/tags/prefix-v2.0
@@ -110,7 +110,7 @@ test_expect_success '--refname-callback sanity check' '
 	(
 		cd refname-sanity-check &&
 
-		test_must_fail git filter-repo --refname-callback "return re.sub(\"tags\", \"other-tags\", refname)" 2>../err &&
+		test_must_fail git filter-repo --refname-callback "return re.sub(b\"tags\", b\"other-tags\", refname)" 2>../err &&
 		test_i18ngrep "fast-import requires tags to be in refs/tags/ namespace" ../err &&
 		rm ../err
 	)
@@ -138,7 +138,7 @@ test_expect_success '--commit-callback' '
                     commit.committer_email = commit.author_email
                     commit.committer_date  = commit.author_date
                     for change in commit.file_changes:
-                      change.mode = \"100755\"
+                      change.mode = b\"100755\"
                     " &&
 		git log --format=%ae%n%ce >log-emails &&
 		! grep committer@example.com log-emails &&
@@ -153,8 +153,8 @@ test_expect_success '--tag-callback' '
 	(
 		cd tag-callback &&
 		git filter-repo --tag-callback "
-                    tag.tagger_name = \"Dr. \"+tag.tagger_name
+                    tag.tagger_name = b\"Dr. \"+tag.tagger_name
-                    tag.message = \"Awesome sauce \"+tag.message
+                    tag.message = b\"Awesome sauce \"+tag.message
                     " &&
 		git cat-file -p v2.0 | grep ^tagger.Dr\\. &&
 		git cat-file -p v2.0 | grep ^Awesome.sauce.Super
@@ -175,7 +175,7 @@ test_expect_success 'callback has return statement sanity check' '
 	(
 		cd callback_return_sanity &&
 
-		test_must_fail git filter-repo --filename-callback "filename + \".txt\"" 2>../err&&
+		test_must_fail git filter-repo --filename-callback "filename + b\".txt\"" 2>../err&&
 		test_i18ngrep "Error: --filename-callback should have a return statement" ../err &&
 		rm ../err
 	)