Merge branch 'thetradedesk-master'

Closes #144

.gitattributes

@@ -0,0 +1,2 @@
+# Set the default behavior, in case people don't have core.autocrlf set.
+* text=auto

.gitignore

@@ -1,2 +1,4 @@
+*.orig
 *.pyc
 .dotest
+.idea/

README.md

@@ -120,6 +120,57 @@ if [ "$3" == "1" ]; then cat; else dos2unix; fi
 -- End of crlf-filter.sh --
 ```
 
+
+Plugins
+-----------------
+
+hg-fast-export supports plugins to manipulate the file data and commit
+metadata. The plugins are enabled with the --plugin option. The value
+of said option is a plugin name (by folder in the plugins directory),
+and optionally, and equals-sign followed by an initialization string.
+
+There is a readme accompanying each of the bundled plugins, with a
+description of the usage. To create a new plugin, one must simply
+add a new folder under the `plugins` directory, with the name of the
+new plugin. Inside, there must be an `__init__.py` file, which contains
+at a minimum:
+
+```
+def build_filter(args):
+    return Filter(args)
+
+class Filter:
+    def __init__(self, args):
+        pass
+        #Or don't pass, if you want to do some init code here
+```
+
+Beyond the boilerplate initialization, you can see the two different
+defined filter methods in the [dos2unix](./plugins/dos2unix) and
+[branch_name_in_commit](./plugins/branch_name_in_commit) plugins.
+
+```
+commit_data = {'branch': branch, 'parents': parents, 'author': author, 'desc': desc}
+
+def commit_message_filter(self,commit_data):
+```
+The `commit_message_filter` method is called for each commit, after parsing
+from hg, but before outputting to git. The dictionary `commit_data` contains the
+above attributes about the commit, and can be modified by any filter. The
+values in the dictionary after filters have been run are used to create the git
+commit.
+
+```
+file_data = {'filename':filename,'file_ctx':file_ctx,'d':d}
+
+def file_data_filter(self,file_data):
+```
+The `file_data_filter` method is called for each file within each commit.
+The dictionary `file_data` contains the above attributes about the file, and
+can be modified by any filter. `file_ctx` is the filecontext from the
+mercurial python library.  After all filters have been run, the values
+are used to add the file to the git commit.
+
 Notes/Limitations
 -----------------
 

hg-fast-export.py

@@ -11,6 +11,7 @@
 import re
 import sys
 import os
+import pluginloader
 
 if sys.platform == "win32":
   # On Windows, sys.stdout is initially opened in text mode, which means that
@@ -123,7 +124,7 @@ def get_author(logmessage,committer,authors):
       return r
   return committer
 
-def export_file_contents(ctx,manifest,files,hgtags,encoding='',filter_contents=None):
+def export_file_contents(ctx,manifest,files,hgtags,encoding='',plugins={}):
   count=0
   max=len(files)
   for file in files:
@@ -137,18 +138,15 @@ def export_file_contents(ctx,manifest,files,hgtags,encoding='',filter_contents=N
       filename=file
     file_ctx=ctx.filectx(file)
     d=file_ctx.data()
-    if filter_contents:
-      import subprocess
-      filter_cmd=filter_contents + [filename,node.hex(file_ctx.filenode()),'1' if file_ctx.isbinary() else '0']
-      try:
-        filter_proc=subprocess.Popen(filter_cmd,stdin=subprocess.PIPE,stdout=subprocess.PIPE)
-        d,_=filter_proc.communicate(d)
-      except:
-        sys.stderr.write('Running filter-contents %s:\n' % filter_cmd)
-        raise
-      filter_ret=filter_proc.poll()
-      if filter_ret:
-        raise subprocess.CalledProcessError(filter_ret,filter_cmd)
+
+    if plugins and plugins['file_data_filters']:
+      file_data = {'filename':filename,'file_ctx':file_ctx,'data':d}
+      for filter in plugins['file_data_filters']:
+        filter(file_data)
+      d=file_data['data']
+      filename=file_data['filename']
+      file_ctx=file_data['file_ctx']
+
     wr('M %s inline %s' % (gitmode(manifest.flags(file)),
                            strip_leading_slash(filename)))
     wr('data %d' % len(d)) # had some trouble with size()
@@ -198,7 +196,8 @@ def strip_leading_slash(filename):
   return filename
 
 def export_commit(ui,repo,revision,old_marks,max,count,authors,
-                  branchesmap,sob,brmap,hgtags,encoding='',fn_encoding='',filter_contents=None):
+                  branchesmap,sob,brmap,hgtags,encoding='',fn_encoding='',
+                  plugins={}):
   def get_branchname(name):
     if brmap.has_key(name):
       return brmap[name]
@@ -211,14 +210,24 @@ def get_branchname(name):
   branch=get_branchname(branch)
 
   parents = [p for p in repo.changelog.parentrevs(revision) if p >= 0]
+  author = get_author(desc,user,authors)
+
+  if plugins and plugins['commit_message_filters']:
+    commit_data = {'branch': branch, 'parents': parents, 'author': author, 'desc': desc}
+    for filter in plugins['commit_message_filters']:
+      filter(commit_data)
+    branch = commit_data['branch']
+    parents = commit_data['parents']
+    author = commit_data['author']
+    desc = commit_data['desc']
 
   if len(parents)==0 and revision != 0:
     wr('reset refs/heads/%s' % branch)
 
   wr('commit refs/heads/%s' % branch)
   wr('mark :%d' % (revision+1))
   if sob:
-    wr('author %s %d %s' % (get_author(desc,user,authors),time,timezone))
+    wr('author %s %d %s' % (author,time,timezone))
   wr('committer %s %d %s' % (user,time,timezone))
   wr('data %d' % (len(desc)+1)) # wtf?
   wr(desc)
@@ -259,8 +268,8 @@ def get_branchname(name):
   removed=[strip_leading_slash(x) for x in removed]
 
   map(lambda r: wr('D %s' % r),removed)
-  export_file_contents(ctx,man,added,hgtags,fn_encoding,filter_contents)
-  export_file_contents(ctx,man,changed,hgtags,fn_encoding,filter_contents)
+  export_file_contents(ctx,man,added,hgtags,fn_encoding,plugins)
+  export_file_contents(ctx,man,changed,hgtags,fn_encoding,plugins)
   wr()
 
   return checkpoint(count)
@@ -396,7 +405,8 @@ def verify_heads(ui,repo,cache,force,branchesmap):
 
 def hg2git(repourl,m,marksfile,mappingfile,headsfile,tipfile,
            authors={},branchesmap={},tagsmap={},
-           sob=False,force=False,hgtags=False,notes=False,encoding='',fn_encoding='',filter_contents=None):
+           sob=False,force=False,hgtags=False,notes=False,encoding='',fn_encoding='',
+           plugins={}):
   def check_cache(filename, contents):
     if len(contents) == 0:
       sys.stderr.write('Warning: %s does not contain any data, this will probably make an incremental import fail\n' % filename)
@@ -438,7 +448,8 @@ def check_cache(filename, contents):
   brmap={}
   for rev in range(min,max):
     c=export_commit(ui,repo,rev,old_marks,max,c,authors,branchesmap,
-                    sob,brmap,hgtags,encoding,fn_encoding,filter_contents)
+                    sob,brmap,hgtags,encoding,fn_encoding,
+                    plugins)
   if notes:
     for rev in range(min,max):
       c=export_note(ui,repo,rev,c,authors, encoding, rev == min and min != 0)
@@ -500,6 +511,10 @@ def bail(parser,opt):
       help="Assume mappings are raw <key>=<value> lines")
   parser.add_option("--filter-contents",dest="filter_contents",
       help="Pipe contents of each exported file through FILTER_CONTENTS <file-path> <hg-hash> <is-binary>")
+  parser.add_option("--plugin-path", type="string", dest="pluginpath",
+      help="Additional search path for plugins ")
+  parser.add_option("--plugin", action="append", type="string", dest="plugins",
+      help="Add a plugin with the given init string <name=init>")
 
   (options,args)=parser.parse_args()
 
@@ -538,13 +553,34 @@ def bail(parser,opt):
   if options.fn_encoding!=None:
     fn_encoding=options.fn_encoding
 
-  filter_contents=None
+  plugins=[]
+  if options.plugins!=None:
+    plugins+=options.plugins
+
   if options.filter_contents!=None:
-    import shlex
-    filter_contents=shlex.split(options.filter_contents)
+    plugins+=['shell_filter_file_contents='+options.filter_contents]
+
+  plugins_dict={}
+  plugins_dict['commit_message_filters']=[]
+  plugins_dict['file_data_filters']=[]
+
+  if plugins and options.pluginpath:
+    sys.stderr.write('Using additional plugin path: ' + options.pluginpath + '\n')
+
+  for plugin in plugins:
+    split = plugin.split('=')
+    name, opts = split[0], '='.join(split[1:])
+    i = pluginloader.get_plugin(name,options.pluginpath)
+    sys.stderr.write('Loaded plugin ' + i['name'] + ' from path: ' + i['path'] +' with opts: ' + opts + '\n')
+    plugin = pluginloader.load_plugin(i).build_filter(opts)
+    if hasattr(plugin,'file_data_filter') and callable(plugin.file_data_filter):
+      plugins_dict['file_data_filters'].append(plugin.file_data_filter)
+    if hasattr(plugin, 'commit_message_filter') and callable(plugin.commit_message_filter):
+      plugins_dict['commit_message_filters'].append(plugin.commit_message_filter)
 
   sys.exit(hg2git(options.repourl,m,options.marksfile,options.mappingfile,
                   options.headsfile, options.statusfile,
                   authors=a,branchesmap=b,tagsmap=t,
                   sob=options.sob,force=options.force,hgtags=options.hgtags,
-                  notes=options.notes,encoding=encoding,fn_encoding=fn_encoding,filter_contents=filter_contents))
+                  notes=options.notes,encoding=encoding,fn_encoding=fn_encoding,
+                  plugins=plugins_dict))

hg-fast-export.sh

@@ -58,6 +58,8 @@ Options:
 	--mappings-are-raw Assume mappings are raw <key>=<value> lines
 	--filter-contents <cmd>  Pipe contents of each exported file through <cmd>
 	                         with <file-path> <hg-hash> <is-binary> as arguments
+	--plugin <plugin=init>  Add a plugin with the given init string (repeatable)
+	--plugin-path <plugin-path> Add an additional plugin lookup path
 "
 case "$1" in
     -h|--help)

pluginloader/__init__.py

@@ -0,0 +1,19 @@
+import os
+import imp
+PluginFolder = os.path.join(os.path.dirname(os.path.realpath(__file__)),"..","plugins")
+MainModule = "__init__"
+
+def get_plugin(name, plugin_path):
+    search_dirs = [PluginFolder]
+    if plugin_path:
+        search_dirs = [plugin_path] + search_dirs
+    for dir in search_dirs:
+        location = os.path.join(dir, name)
+        if not os.path.isdir(location) or not MainModule + ".py" in os.listdir(location):
+            continue
+        info = imp.find_module(MainModule, [location])
+        return {"name": name, "info": info, "path": location}
+    raise Exception("Could not find plugin with name " + name)
+
+def load_plugin(plugin):
+    return imp.load_module(MainModule, *plugin["info"])

plugins/branch_name_in_commit/README.md

@@ -0,0 +1,10 @@
+## Branch Name in Commit Message
+
+Mercurial has a much stronger notion of branches than Git,
+and some parties may not wish to lose the branch information
+during the migration to Git. You can use this plugin to either
+prepend or append the branch name from the mercurial
+commit into the commit message in Git.
+
+To use the plugin, add
+`--plugin branch_name_in_commit=(start|end)`.

plugins/branch_name_in_commit/__init__.py

@@ -0,0 +1,14 @@
+def build_filter(args):
+    return Filter(args)
+
+class Filter:
+    def __init__(self, args):
+        if not args in ['start','end']:
+            raise Exception('Cannot have branch name anywhere but start and end')
+        self.pos = args
+
+    def commit_message_filter(self,commit_data):
+        if self.pos == 'start':
+            commit_data['desc'] = commit_data['branch'] + '\n' + commit_data['desc']
+        if self.pos == 'end':
+            commit_data['desc'] = commit_data['desc'] + '\n' + commit_data['branch']

plugins/dos2unix/README.md

@@ -0,0 +1,9 @@
+## Dos2unix filter
+
+This plugin converts CRLF line ending to LF in text files in the repo.
+It is recommended that you have a .gitattributes file that maintains
+the usage of LF endings going forward, for after you have converted your
+repository.
+
+To use the plugin, add
+`--plugin dos2unix`.

plugins/dos2unix/__init__.py

@@ -0,0 +1,11 @@
+def build_filter(args):
+    return Filter(args)
+
+class Filter():
+    def __init__(self, args):
+        pass
+
+    def file_data_filter(self,file_data):
+        file_ctx = file_data['file_ctx']
+        if not file_ctx.isbinary():
+            file_data['data'] = file_data['data'].replace('\r\n', '\n')

plugins/shell_filter_file_contents/README.md

@@ -0,0 +1,30 @@
+## Shell Script File Filter
+
+This plugin uses shell scripts in order to perform filtering of files.
+If your preferred scripting is done via shell, this tool is for you.
+Be noted, though, that this method can cause an order of magnitude slow
+down. For small repositories, this wont be an issue.
+
+To use the plugin, add
+`--plugin shell_filter_file_contents=path/to/shell/script.sh`.
+The filter script is supplied to the plugin option after the plugin name,
+which is in turned passed to the plugin initialization. hg-fast-export
+runs the filter for each exported file, pipes its content to the filter's
+standard input, and uses the filter's standard output in place
+of the file's original content. An example use of this feature
+is to convert line endings in text files from CRLF to git's preferred LF,
+although this task is faster performed using the native plugin.
+
+The script is called with the following syntax:
+`FILTER_CONTENTS <file-path> <hg-hash> <is-binary>`
+
+```
+-- Start of crlf-filter.sh --
+#!/bin/sh
+# $1 = pathname of exported file relative to the root of the repo
+# $2 = Mercurial's hash of the file
+# $3 = "1" if Mercurial reports the file as binary, otherwise "0"
+
+if [ "$3" == "1" ]; then cat; else dos2unix; fi
+-- End of crlf-filter.sh --
+```

plugins/shell_filter_file_contents/__init__.py

@@ -0,0 +1,28 @@
+#Pipe contents of each exported file through FILTER_CONTENTS <file-path> <hg-hash> <is-binary>"
+import subprocess
+import shlex
+import sys
+from mercurial import node
+
+def build_filter(args):
+    return Filter(args)
+
+class Filter:
+    def __init__(self, args):
+        self.filter_contents = shlex.split(args)
+
+    def file_data_filter(self,file_data):
+        d = file_data['data']
+        file_ctx = file_data['file_ctx']
+        filename = file_data['filename']
+        filter_cmd = self.filter_contents + [filename, node.hex(file_ctx.filenode()), '1' if file_ctx.isbinary() else '0']
+        try:
+            filter_proc = subprocess.Popen(filter_cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
+            d, _ = filter_proc.communicate(d)
+        except:
+            sys.stderr.write('Running filter-contents %s:\n' % filter_cmd)
+            raise
+        filter_ret = filter_proc.poll()
+        if filter_ret:
+            raise subprocess.CalledProcessError(filter_ret, filter_cmd)
+        file_data['data'] = d