Implemented multi-line parsing of git-config to the point where a sepcific test-file is working.

This brings us much closer to what git can do, and should at least prevent errors while reading
configuration files (which would break a lot of features, like handling of remotes since these rely
reading configuration files).

Fixes #112

3 files changed, 271 insertions, 39 deletions

diff --git a/git/config.py b/git/config.py
index eefab299..5828a1c1 100644
--- a/git/config.py
+++ b/git/config.py
@@ -22,7 +22,8 @@ from git.compat import (
     string_types,
     FileType,
     defenc,
-    with_metaclass
+    with_metaclass,
+    PY3
 )
 
 __all__ = ('GitConfigParser', 'SectionConstraint')
@@ -243,7 +244,21 @@ class GitConfigParser(with_metaclass(MetaParserBuilder, cp.RawConfigParser, obje
         cursect = None                            # None, or a dictionary
         optname = None
         lineno = 0
+        is_multi_line = False
         e = None                                  # None, or an exception
+
+        def string_decode(v):
+            if v[-1] == '\\':
+                v = v[:-1]
+            # end cut trailing escapes to prevent decode error
+
+            if PY3:
+                return v.encode(defenc).decode('unicode_escape')
+            else:
+                return v.decode('string_escape')
+            # end
+        # end
+
         while True:
             # we assume to read binary !
             line = fp.readline().decode(defenc)
@@ -256,46 +271,60 @@ class GitConfigParser(with_metaclass(MetaParserBuilder, cp.RawConfigParser, obje
             if line.split(None, 1)[0].lower() == 'rem' and line[0] in "rR":
                 # no leading whitespace
                 continue
-            else:
-                # is it a section header?
-                mo = self.SECTCRE.match(line.strip())
+
+            # is it a section header?
+            mo = self.SECTCRE.match(line.strip())
+            if not is_multi_line and mo:
+                sectname = mo.group('header').strip()
+                if sectname in self._sections:
+                    cursect = self._sections[sectname]
+                elif sectname == cp.DEFAULTSECT:
+                    cursect = self._defaults
+                else:
+                    cursect = self._dict((('__name__', sectname),))
+                    self._sections[sectname] = cursect
+                    self._proxies[sectname] = None
+                # So sections can't start with a continuation line
+                optname = None
+            # no section header in the file?
+            elif cursect is None:
+                raise cp.MissingSectionHeaderError(fpname, lineno, line)
+            # an option line?
+            elif not is_multi_line:
+                mo = self.OPTCRE.match(line)
                 if mo:
-                    sectname = mo.group('header').strip()
-                    if sectname in self._sections:
-                        cursect = self._sections[sectname]
-                    elif sectname == cp.DEFAULTSECT:
-                        cursect = self._defaults
-                    else:
-                        cursect = self._dict((('__name__', sectname),))
-                        self._sections[sectname] = cursect
-                        self._proxies[sectname] = None
-                    # So sections can't start with a continuation line
-                    optname = None
-                # no section header in the file?
-                elif cursect is None:
-                    raise cp.MissingSectionHeaderError(fpname, lineno, line)
-                # an option line?
+                    # We might just have handled the last line, which could contain a quotation we want to remove
+                    optname, vi, optval = mo.group('option', 'vi', 'value')
+                    if vi in ('=', ':') and ';' in optval:
+                        pos = optval.find(';')
+                        if pos != -1 and optval[pos - 1].isspace():
+                            optval = optval[:pos]
+                    optval = optval.strip()
+                    if optval == '""':
+                        optval = ''
+                    # end handle empty string
+                    optname = self.optionxform(optname.rstrip())
+                    if len(optval) > 1 and optval[0] == '"' and optval[-1] != '"':
+                        is_multi_line = True
+                        optval = string_decode(optval[1:])
+                    # end handle multi-line
+                    cursect[optname] = optval
                 else:
-                    mo = self.OPTCRE.match(line)
-                    if mo:
-                        optname, vi, optval = mo.group('option', 'vi', 'value')
-                        if vi in ('=', ':') and ';' in optval:
-                            pos = optval.find(';')
-                            if pos != -1 and optval[pos - 1].isspace():
-                                optval = optval[:pos]
-                        optval = optval.strip()
-                        if optval == '""':
-                            optval = ''
-                        optname = self.optionxform(optname.rstrip())
-                        cursect[optname] = optval
-                    else:
-                        if not e:
-                            e = cp.ParsingError(fpname)
-                        e.append(lineno, repr(line))
-                    # END
-                # END ?
-            # END ?
+                    if not e:
+                        e = cp.ParsingError(fpname)
+                    e.append(lineno, repr(line))
+                    print(lineno, line)
+                    continue
+            else:
+                line = line.rstrip()
+                if line.endswith('"'):
+                    is_multi_line = False
+                    line = line[:-1]
+                # end handle quotations
+                cursect[optname] += string_decode(line)
+            # END parse section or option
         # END while reading
+
         # if any parsing errors occurred, raise an exception
         if e:
             raise e
diff --git a/git/test/fixtures/git_config_with_comments b/git/test/fixtures/git_config_with_comments
new file mode 100644
index 00000000..e9d4443d
--- /dev/null
+++ b/git/test/fixtures/git_config_with_comments
@@ -0,0 +1,183 @@
+[user]
+  name = Cody Veal
+  email = cveal05@gmail.com
+
+[github]
+  user = cjhveal
+
+[advice]
+  statusHints = false
+
+[alias]
+  # add
+  a = add
+  aa = add --all
+  ap = add --patch
+
+  aliases = !git config --list | grep 'alias\\.' | sed 's/alias\\.\\([^=]*\\)=\\(.*\\)/\\1\\\t => \\2/' | sort
+
+  # branch
+  br = branch
+  branches = branch -av
+  cp = cherry-pick
+  diverges = !bash -c 'diff -u <(git rev-list --first-parent "${1}") <(git rev-list --first-parent "${2:-HEAD}"g | sed -ne \"s/^ //p\" | head -1' -
+  track = checkout -t
+  nb = checkout -b
+
+  # commit
+  amend = commit --amend -C HEAD
+  c = commit
+	ca = commit --amend
+	cm = commit --message
+	msg = commit --allow-empty -m
+
+  co = checkout
+
+  # diff
+  d = diff --color-words # diff by word
+  ds = diff --staged --color-words
+  dd = diff --color-words=. # diff by char
+  dds = diff --staged --color-words=.
+  dl = diff # diff by line
+  dls = diff --staged
+
+  h = help
+
+  # log
+	authors = "!git log --pretty=format:%aN | sort | uniq -c | sort -rn"
+  lc = log ORIG_HEAD.. --stat --no-merges
+  lg = log --graph --pretty=format:'%Cred%h%Creset -%C(yellow)%d%Creset %s %Cgreen(%cr)%Creset' --abbrev-commit --date=relative
+  lol = log --graph --decorate --pretty=oneline --abbrev-commit
+  lola = log --graph --decorate --pretty=oneline --abbrev-commit --all
+
+  # merge
+	m = merge
+	mm = merge --no-ff
+  ours   = "!f() { git checkout --ours $@ && git add $@; }; f"
+  theirs = "!f() { git checkout --theirs $@ && git add $@; }; f"
+
+  # push/pull
+  l = pull
+  p = push
+  sync = !git pull && git push
+
+  # remotes
+	prune-remotes = "!for remote in `git remote`; do git remote prune $remote; done"
+  r = remote
+
+  # rebase
+  rb = rebase
+  rba = rebase --abort
+  rbc = rebase --continue
+  rbs = rebase --skip
+
+  # reset
+  rh = reset --hard
+  rhh = reset HEAD --hard
+	uncommit = reset --soft HEAD^
+  unstage = reset HEAD --
+  unpush = push -f origin HEAD^:master
+
+  # stash
+  ss = stash
+  sl = stash list
+  sp = stash pop
+  sd = stash drop
+  snapshot = !git stash save "snapshot: $(date)" && git stash apply "stash@{0}"
+
+  # status
+  s = status --short --branch
+  st = status
+
+  # submodule
+	sm = submodule
+	sma = submodule add
+	smu = submodule update --init
+  pup = !git pull && git submodule init && git submodule update
+
+  # file level ignoring
+  assume   = update-index --assume-unchanged
+  unassume = update-index --no-assume-unchanged
+  assumed  = "!git ls-files -v | grep ^h | cut -c 3-"
+
+
+[apply]
+  whitespace = fix
+
+[color]
+  ui = auto
+
+[color "branch"]
+  current = yellow reverse
+  local = yellow
+  remote = green
+
+[color "diff"]
+  meta = yellow
+  frag = magenta
+  old = red bold
+  new = green bold
+  whitespace = red reverse
+
+[color "status"]
+  added = green
+  changed = yellow
+  untracked = cyan
+
+[core]
+  editor = /usr/bin/vim
+  excludesfile = ~/.gitignore_global
+	attributesfile = ~/.gitattributes
+
+[diff]
+	renames = copies
+	mnemonicprefix = true
+
+[diff "zip"]
+  textconv = unzip -c -a
+
+[merge]
+  log = true
+
+[merge "railsschema"]
+	name = newer Rails schema version
+	driver = "ruby -e '\n\
+		system %(git), %(merge-file), %(--marker-size=%L), %(%A), %(%O), %(%B)\n\
+		b = File.read(%(%A))\n\
+		b.sub!(/^<+ .*\\nActiveRecord::Schema\\.define.:version => (\\d+). do\\n=+\\nActiveRecord::Schema\\.define.:version => (\\d+). do\\n>+ .*/) do\n\
+		  %(ActiveRecord::Schema.define(:version => #{[$1, $2].max}) do)\n\
+		end\n\
+		File.open(%(%A), %(w)) {|f| f.write(b)}\n\
+		exit 1 if b.include?(%(<)*%L)'"
+
+[merge "gemfilelock"]
+  name = relocks the gemfile.lock
+  driver = bundle lock
+
+[pager]
+  color = true
+
+[push]
+  default = upstream
+
+[rerere]
+  enabled = true
+
+[url "git@github.com:"]
+  insteadOf = "gh:"
+  pushInsteadOf = "github:"
+  pushInsteadOf = "git://github.com/"
+
+[url "git://github.com/"]
+  insteadOf = "github:"
+
+[url "git@gist.github.com:"]
+  insteadOf = "gst:"
+  pushInsteadOf = "gist:"
+  pushInsteadOf = "git://gist.github.com/"
+
+[url "git://gist.github.com/"]
+  insteadOf = "gist:"
+
+[url "git@heroku.com:"]
+  insteadOf = "heroku:"
diff --git a/git/test/test_config.py b/git/test/test_config.py
index 546a2fe1..9000c07f 100644
--- a/git/test/test_config.py
+++ b/git/test/test_config.py
@@ -3,10 +3,13 @@
 #
 # This module is part of GitPython and is released under
 # the BSD License: http://www.opensource.org/licenses/bsd-license.php
+# The test test_multi_line_config requires whitespace (especially tabs) to remain
+# flake8: noqa
 
 from git.test.lib import (
     TestCase,
-    fixture_path
+    fixture_path,
+    assert_equal
 )
 from git import (
     GitConfigParser
@@ -72,6 +75,23 @@ class TestBase(TestCase):
             assert r_config.get(sname, oname) == val
         # END for each filename
 
+    def test_multi_line_config(self):
+        file_obj = self._to_memcache(fixture_path("git_config_with_comments"))
+        config = GitConfigParser(file_obj, read_only=False)
+        ev = r"""ruby -e '
+		system %(git), %(merge-file), %(--marker-size=%L), %(%A), %(%O), %(%B)
+		b = File.read(%(%A))
+		b.sub!(/^<+ .*\nActiveRecord::Schema\.define.:version => (\d+). do\n=+\nActiveRecord::Schema\.define.:version => (\d+). do\n>+ .*/) do
+		  %(ActiveRecord::Schema.define(:version => #{[$1, $2].max}) do)
+		end
+		File.open(%(%A), %(w)) {|f| f.write(b)}
+		exit 1 if b.include?(%(<)*%L)'"""
+        assert_equal(config.get('merge "railsschema"', 'driver'), ev)
+        assert_equal(config.get('alias', 'lg'),
+                     "log --graph --pretty=format:'%Cred%h%Creset -%C(yellow)%d%Creset %s %Cgreen(%cr)%Creset'"
+                     " --abbrev-commit --date=relative")
+        assert len(config.sections()) == 23
+
     def test_base(self):
         path_repo = fixture_path("git_config")
         path_global = fixture_path("git_config_global")