Merge lp:~jml/gtg/better-lint-checking into lp:~gtg/gtg/old-trunk

[Jonathan Lange]

[Jonathan Lange (jml)]

This branch tries to improve both the way that lint checking is done and also how well we do at those lint checks.

Most of the size of the branch is made up from adding pep8.py to scripts. It's an MIT licensed script, and should be OK to distribute with this GPLv3 app.

The next biggest change is making dbuswrapper use 4 space indentation, like every other Python module in the known universe :)

Another interesting change is removing the '_' hack to __builtins__ and instead requiring scripts to import _ from GTG. This change, together with removal of '*' imports and a few other tweaks means that pyflakes returns a clean bill of health. Note that * imports make pyflakes less useful, since with them it can't detect unrecognized names.

I've also got rid of some tabs and replaced them with spaces.

The most interesting change is that 'make lint' now runs pyflakes and pep8 checks on the code base. Although I've updated codecheck.sh so that the sillier warnings are now disabled, I think that 'make lint' should become the standard way of doing a lint check.

[lp:~jml/gtg/better-lint-checking]

278. By Jonathan Lange on 2009-07-14

Remove codecheck.sh -- let's use 'make lint' instead.

279. By Jonathan Lange on 2009-07-14

Later version of PEP 8. Drop the warning filters

280. By Jonathan Lange on 2009-07-14

Update comments in Makefile.

=== modified file 'GTG/__init__.py'
--- GTG/__init__.py	2009-07-12 22:05:07 +0000
+++ GTG/__init__.py	2009-07-13 10:22:44 +0000
@@ -96,8 +96,8 @@
 translation = gettext.translation(GETTEXT_DOMAIN, LOCALE_PATH,
                                   languages=languages_used,
                                   fallback=True)
-import __builtin__
-__builtin__._ = translation.gettext
+
+_ = translation.gettext
 
 #GTG directories setup
 if not os.path.isdir( os.path.join(LOCAL_ROOTDIR,'data') ) :
 
=== modified file 'GTG/backends/localfile.py'
--- GTG/backends/localfile.py	2009-04-02 22:03:26 +0000
+++ GTG/backends/localfile.py	2009-07-13 09:20:43 +0000
@@ -21,7 +21,7 @@
 #Localfile is a read/write backend that will store your tasks in an XML file
 #This file will be in your $XDG_DATA_DIR/gtg folder.
 
-import os,shutil
+import os
 import uuid
 
 from GTG.core  import CoreConfig
 
=== modified file 'GTG/core/__init__.py'
--- GTG/core/__init__.py	2009-06-18 08:56:33 +0000
+++ GTG/core/__init__.py	2009-07-13 10:26:28 +0000
@@ -45,11 +45,10 @@
 
 #=== IMPORT ====================================================================
 import os
-from xdg.BaseDirectory import *
+from xdg.BaseDirectory import xdg_data_home, xdg_config_home
 from GTG.tools         import cleanxml
 from configobj         import ConfigObj
 
-import GTG
 from GTG.core          import firstrun_tasks
 
 class CoreConfig:
 
=== modified file 'GTG/core/dbuswrapper.py'
--- GTG/core/dbuswrapper.py	2009-07-09 20:03:12 +0000
+++ GTG/core/dbuswrapper.py	2009-07-13 09:13:22 +0000
@@ -1,120 +1,133 @@
-import gobject, dbus.glib, dbus, dbus.service
+import dbus
+import dbus.glib
+import dbus.service
+
 
 BUSNAME = "org.GTG"
 
 def dsanitize(data):
-  # Clean up a dict so that it can be transmitted through D-Bus
-  for k, v in data.items():
-    # Manually specify an arbitrary content type for empty Python arrays
-    # because D-Bus can't handle the type conversion for empty arrays
-    if not v and isinstance(v, list):
-      data[k] = dbus.Array([], "s")
-    # D-Bus has no concept of a null or empty value so we have to convert None
-    # types to something else. I use an empty string because it has the same
-    # behavior as None in a Python conditional expression
-    elif v == None:
-      data[k] = ""
-
-  return data
+    # Clean up a dict so that it can be transmitted through D-Bus
+    for k, v in data.items():
+        # Manually specify an arbitrary content type for empty Python arrays
+        # because D-Bus can't handle the type conversion for empty arrays
+        if not v and isinstance(v, list):
+            data[k] = dbus.Array([], "s")
+        # D-Bus has no concept of a null or empty value so we have to convert
+        # None types to something else. I use an empty string because it has
+        # the same behavior as None in a Python conditional expression
+        elif v == None:
+            data[k] = ""
+
+    return data
+
 
 def task_to_dict(task):
-  # Translate a task object into a D-Bus dictionary
-  return dbus.Dictionary(dsanitize({
-      "id": task.get_id(),
-      "status": task.get_status(),
-      "title": task.get_title(),
-      "duedate": task.get_due_date(),
-      "startdate": task.get_start_date(),
-      "donedate": task.get_closed_date(),
-      "tags": task.get_tags_name(),
-      "text": task.get_text(),
-      "subtask": task.get_subtasks_tid(),
-    }), signature="sv")
+    # Translate a task object into a D-Bus dictionary
+    return dbus.Dictionary(dsanitize({
+          "id": task.get_id(),
+          "status": task.get_status(),
+          "title": task.get_title(),
+          "duedate": task.get_due_date(),
+          "startdate": task.get_start_date(),
+          "donedate": task.get_closed_date(),
+          "tags": task.get_tags_name(),
+          "text": task.get_text(),
+          "subtask": task.get_subtasks_tid(),
+          }), signature="sv")
+
 
 class DBusTaskWrapper(dbus.service.Object):
-  # D-Bus service object that exposes GTG's task store to third-party apps
-  def __init__(self, req, ui):
-    # Attach the object to D-Bus
-    self.bus = dbus.SessionBus()
-    bus_name = dbus.service.BusName(BUSNAME, bus=self.bus)
-    dbus.service.Object.__init__(self, bus_name, "/org/GTG")
-    self.req = req
-    self.ui = ui
-
-  @dbus.service.method(BUSNAME)
-  def get_task_ids(self):
-    # Retrieve a list of task ID values
-    return self.req.get_tasks_list(status=["Active", "Done"], started_only=False)
-
-  @dbus.service.method(BUSNAME)
-  def get_task(self, tid):
-    # Retrieve a specific task by ID and return the data
-    return task_to_dict(self.req.get_task(tid))
-
-  @dbus.service.method(BUSNAME)
-  def get_tasks(self):
-    # Retrieve a list of task data dicts
-    return [self.get_task(id) for id in self.get_task_ids()]
-
-  @dbus.service.method(BUSNAME, in_signature="asasbb")
-  def get_task_ids_filtered(self, tags, status, started_only, is_root):
-    # Retrieve a list of task IDs filtered by specified parameters
-    ids = self.req.get_tasks_list(tags, status, False, started_only, is_root)
-    # If there are no matching tasks, return an empty D-Bus array
-    return ids if ids else dbus.Array([], "s")
-
-  @dbus.service.method(BUSNAME, in_signature="asasbb")
-  def get_tasks_filtered(self, tags, status, started_only, is_root):
-    # Retrieve a list of task data discts filtered by specificed parameters
-    tasks = self.get_task_ids_filtered(tags, status, started_only, is_root)
-    # If no tasks match the filter, return an empty D-Bus array
-    return [self.get_task(id) for id in tasks] if tasks else dbus.Array([], "s")
-
-  @dbus.service.method(BUSNAME)
-  def has_task(self, tid):
-    return self.req.has_task(tid)
-
-  @dbus.service.method(BUSNAME)
-  def delete_task(self, tid):
-    self.req.delete_task(tid)
-
-  @dbus.service.method(BUSNAME, in_signature="sssssassas")
-  def new_task(self, status, title, duedate, startdate, donedate, tags, text, subtasks):
-    # Generate a new task object and return the task data as a dict
-    nt = self.req.new_task()
-    for sub in subtasks: nt.add_subtask(sub)
-    for tag in tags: nt.add_tag(tag)
-    nt.set_status(status, donedate=donedate)
-    nt.set_title(title)
-    nt.set_due_date(duedate)
-    nt.set_start_date(startdate)
-    nt.set_text(text)
-    return task_to_dict(nt)
-
-  @dbus.service.method(BUSNAME)
-  def modify_task(self, tid, task_data):
-    # Apply supplied task data to the task object with the specified ID
-    task = self.req.get_task(tid)
-    task.set_status(task_data["status"], donedate=task_data["donedate"])
-    task.set_title(task_data["title"])
-    task.set_due_date(task_data["duedate"])
-    task.set_start_date(task_data["startdate"])
-    task.set_text(task_data["text"])
-
-    for tag in task_data["tags"]: task.add_tag(tag)
-    for sub in task_data["subtask"]: task.add_subtask(sub)
-    return task_to_dict(task)
-
-  @dbus.service.method(BUSNAME)
-  def open_task_editor(self, tid):
-    self.ui.open_task(tid)
-
-  @dbus.service.method(BUSNAME)
-  def hide_task_browser(self):
-    self.ui.window.hide()
-  
-  @dbus.service.method(BUSNAME)
-  def show_task_browser(self):
-    self.ui.window.present()
-    self.ui.window.move(self.ui.priv["window_xpos"], self.ui.priv["window_ypos"])
-
+
+    # D-Bus service object that exposes GTG's task store to third-party apps
+    def __init__(self, req, ui):
+        # Attach the object to D-Bus
+        self.bus = dbus.SessionBus()
+        bus_name = dbus.service.BusName(BUSNAME, bus=self.bus)
+        dbus.service.Object.__init__(self, bus_name, "/org/GTG")
+        self.req = req
+        self.ui = ui
+
+    @dbus.service.method(BUSNAME)
+    def get_task_ids(self):
+        # Retrieve a list of task ID values
+        return self.req.get_tasks_list(
+          status=["Active", "Done"], started_only=False)
+
+    @dbus.service.method(BUSNAME)
+    def get_task(self, tid):
+        # Retrieve a specific task by ID and return the data
+        return task_to_dict(self.req.get_task(tid))
+
+    @dbus.service.method(BUSNAME)
+    def get_tasks(self):
+        # Retrieve a list of task data dicts
+        return [self.get_task(id) for id in self.get_task_ids()]
+
+    @dbus.service.method(BUSNAME, in_signature="asasbb")
+    def get_task_ids_filtered(self, tags, status, started_only, is_root):
+        # Retrieve a list of task IDs filtered by specified parameters
+        ids = self.req.get_tasks_list(
+            tags, status, False, started_only, is_root)
+        # If there are no matching tasks, return an empty D-Bus array
+        return ids if ids else dbus.Array([], "s")
+
+    @dbus.service.method(BUSNAME, in_signature="asasbb")
+    def get_tasks_filtered(self, tags, status, started_only, is_root):
+        # Retrieve a list of task data discts filtered by specificed parameters
+        tasks = self.get_task_ids_filtered(
+            tags, status, started_only, is_root)
+        # If no tasks match the filter, return an empty D-Bus array
+        if tasks:
+            return [self.get_task(id) for id in tasks]
+        else:
+            return dbus.Array([], "s")
+
+    @dbus.service.method(BUSNAME)
+    def has_task(self, tid):
+        return self.req.has_task(tid)
+
+    @dbus.service.method(BUSNAME)
+    def delete_task(self, tid):
+        self.req.delete_task(tid)
+
+    @dbus.service.method(BUSNAME, in_signature="sssssassas")
+    def new_task(self, status, title, duedate, startdate, donedate, tags,
+                 text, subtasks):
+        # Generate a new task object and return the task data as a dict
+        nt = self.req.new_task()
+        for sub in subtasks: nt.add_subtask(sub)
+        for tag in tags: nt.add_tag(tag)
+        nt.set_status(status, donedate=donedate)
+        nt.set_title(title)
+        nt.set_due_date(duedate)
+        nt.set_start_date(startdate)
+        nt.set_text(text)
+        return task_to_dict(nt)
+
+    @dbus.service.method(BUSNAME)
+    def modify_task(self, tid, task_data):
+        # Apply supplied task data to the task object with the specified ID
+        task = self.req.get_task(tid)
+        task.set_status(task_data["status"], donedate=task_data["donedate"])
+        task.set_title(task_data["title"])
+        task.set_due_date(task_data["duedate"])
+        task.set_start_date(task_data["startdate"])
+        task.set_text(task_data["text"])
+
+        for tag in task_data["tags"]: task.add_tag(tag)
+        for sub in task_data["subtask"]: task.add_subtask(sub)
+        return task_to_dict(task)
+
+    @dbus.service.method(BUSNAME)
+    def open_task_editor(self, tid):
+        self.ui.open_task(tid)
+
+    @dbus.service.method(BUSNAME)
+    def hide_task_browser(self):
+        self.ui.window.hide()
+
+    @dbus.service.method(BUSNAME)
+    def show_task_browser(self):
+        self.ui.window.present()
+        self.ui.window.move(
+          self.ui.priv["window_xpos"], self.ui.priv["window_ypos"])
 
=== modified file 'GTG/core/firstrun_tasks.py'
--- GTG/core/firstrun_tasks.py	2009-06-18 08:37:25 +0000
+++ GTG/core/firstrun_tasks.py	2009-07-13 10:22:44 +0000
@@ -1,3 +1,4 @@
+from GTG import _
 from GTG.tools import cleanxml
 
 def populate():
 
=== modified file 'GTG/core/requester.py'
--- GTG/core/requester.py	2009-07-13 08:57:44 +0000
+++ GTG/core/requester.py	2009-07-13 10:26:28 +0000
@@ -18,7 +18,7 @@
 # -----------------------------------------------------------------------------
 
 
-from GTG.tools.listes import *
+from GTG.tools.listes import returnlist
 
 #Requester is a pure View object. It will not do anything but it will
 #be used by any Interface to handle the requests to the datastore
 
=== modified file 'GTG/core/task.py'
--- GTG/core/task.py	2009-07-13 08:57:44 +0000
+++ GTG/core/task.py	2009-07-13 10:26:28 +0000
@@ -20,8 +20,10 @@
 from datetime import date
 import xml.dom.minidom
 
-from GTG.tools.dates import *
-from GTG.tools.listes import *
+from GTG import _
+from GTG.tools.dates import strtodate
+from GTG.tools.listes import returnlist
+
 
 #This class represent a task in GTG.
 #You should never create a Task directly. Use the datastore.new_task() function.
 
=== modified file 'GTG/gtg.py'
--- GTG/gtg.py	2009-07-09 08:31:53 +0000
+++ GTG/gtg.py	2009-07-13 10:22:44 +0000
@@ -46,6 +46,7 @@
 import sys, os
 
 #our own imports
+from GTG import _
 from GTG.taskbrowser.browser import TaskBrowser
 from GTG.core.datastore      import DataStore
 from GTG.core.dbuswrapper    import DBusTaskWrapper
 
=== modified file 'GTG/taskbrowser/__init__.py'
--- GTG/taskbrowser/__init__.py	2009-04-03 15:00:18 +0000
+++ GTG/taskbrowser/__init__.py	2009-07-13 10:22:44 +0000
@@ -22,6 +22,8 @@
 #simple, HIG compliant and well integrated with Gnome.
 import os
 
+from GTG import _
+
 class GnomeConfig :
     current_rep = os.path.dirname(os.path.abspath(__file__))
     GLADE_FILE    = os.path.join(current_rep,"taskbrowser.glade")
 
=== modified file 'GTG/taskbrowser/browser.py'
--- GTG/taskbrowser/browser.py	2009-07-13 02:40:17 +0000
+++ GTG/taskbrowser/browser.py	2009-07-13 10:41:18 +0000
@@ -1,4 +1,5 @@
 # -*- coding: utf-8 -*-
+# pylint: disable-msg=W0201
 # -----------------------------------------------------------------------------
 # Gettings Things Gnome! - a personnal organizer for the GNOME desktop
 # Copyright (c) 2008-2009 - Lionel Dricot & Bertrand Rousseau
@@ -33,6 +34,7 @@
 
 #our own imports
 import GTG
+from GTG import _
 from GTG.taskeditor.editor            import TaskEditor
 from GTG.taskbrowser.CellRendererTags import CellRendererTags
 from GTG.taskbrowser                  import GnomeConfig
@@ -507,15 +509,15 @@
               }
         wTree.signal_autoconnect(dic)
         window = wTree.get_widget("ColorChooser")
-	# Get previous color
+        # Get previous color
         tags,notag_only = self.get_selected_tags() #pylint: disable-msg=W0612
         if len(tags) == 1:
-                color = tags[0].get_attribute("color")
-                if color != None:
-			colorspec = gtk.gdk.Color(color)
-			colorsel = window.colorsel
-			colorsel.set_previous_color(colorspec)
-			colorsel.set_current_color(colorspec)
+            color = tags[0].get_attribute("color")
+            if color != None:
+                colorspec = gtk.gdk.Color(color)
+                colorsel = window.colorsel
+                colorsel.set_previous_color(colorspec)
+                colorsel.set_current_color(colorspec)
         window.show()
 
     def on_color_response(self,widget,response) :
@@ -653,7 +655,7 @@
             return False
         year,month,day = splited_date
         try :
-            date = datetime.date(int(year),int(month),int(day))
+            datetime.date(int(year),int(month),int(day))
         except ValueError :
             return False
         else :
 
=== modified file 'GTG/taskeditor/__init__.py'
--- GTG/taskeditor/__init__.py	2009-06-10 13:17:47 +0000
+++ GTG/taskeditor/__init__.py	2009-07-13 10:22:44 +0000
@@ -20,6 +20,8 @@
 
 import os
 
+from GTG import _
+
 class GnomeConfig :
     current_rep = os.path.dirname(os.path.abspath(__file__))
     GLADE_FILE    = os.path.join(current_rep,"taskeditor.glade")
 
=== modified file 'GTG/taskeditor/editor.py'
--- GTG/taskeditor/editor.py	2009-06-10 13:17:47 +0000
+++ GTG/taskeditor/editor.py	2009-07-13 10:41:18 +0000
@@ -26,18 +26,19 @@
 import time
 from datetime import date
 
+from GTG import _
 from GTG.taskeditor          import GnomeConfig
 from GTG.tools               import dates
 from GTG.taskeditor.taskview import TaskView
 try:
     import pygtk
     pygtk.require("2.0")
-except:
+except: # pylint: disable-msg=W0702
     sys.exit(1)
 try:
     import gtk
     from gtk import gdk
-except:
+except: # pylint: disable-msg=W0702
     sys.exit(1)
     
 date_separator = "/"
 
=== modified file 'GTG/taskeditor/taskview.py'
--- GTG/taskeditor/taskview.py	2009-06-04 19:59:15 +0000
+++ GTG/taskeditor/taskview.py	2009-07-13 09:20:43 +0000
@@ -909,11 +909,11 @@
             for ta in itera.get_toggled_tags(False) :
                 if ta.get_data('is_subtask') :
                     subtask_nbr = ta.get_data('child')
-            
+
         #New line : the user pressed enter !
         #If the line begins with "-", it's a new subtask !
         if tex == '\n' :
-            insert_point = self.buff.create_mark("insert_point",itera,True)
+            self.buff.create_mark("insert_point", itera, True)
             #First, we close tag tags.
             #If we are at the end of a tag, we look for closed tags
             closed_tag = None
@@ -923,7 +923,6 @@
             #Or maybe we are in the middle of a tag
             else :
                 list_stag = itera.get_tags()
-            stag = None
             for t in list_stag :
                 if t.get_data('is_tag') :
                     closed_tag = t.get_data('tagname')
@@ -984,17 +983,15 @@
                 self.buff.create_mark(anchor,itera,True)
                 self.buff.create_mark("/%s"%anchor,itera,False)
         self.insert_sigid = self.buff.connect('insert-text', self._insert_at_cursor)
-        self.keypress_sigid = self.connect('key_press_event', self._keypress)
+        self.connect('key_press_event', self._keypress)
         self.modified_sigid = self.buff.connect("changed" , self.modified)
         
     def _keypress(self, widget, event):
         # Check for Ctrl-Return/Enter
         if event.state & gtk.gdk.CONTROL_MASK and event.keyval in (gtk.keysyms.Return, gtk.keysyms.KP_Enter):
-            buff = self.buff   
+            buff = self.buff
             cursor_mark = buff.get_insert()
             cursor_iter = buff.get_iter_at_mark(cursor_mark)
-            table = buff.get_tag_table()
-			
             local_start = cursor_iter.copy()
 
             for tag in local_start.get_tags():
@@ -1005,7 +1002,7 @@
                         self.open_task(anchor)
                     elif typ == "http" :
                         openurl.openurl(anchor)
-					
+
             return True
 
     #Deindent the current line of one level
 
=== added file 'Makefile'
--- Makefile	1970-01-01 00:00:00 +0000
+++ Makefile	2009-07-13 10:59:58 +0000
@@ -0,0 +1,13 @@
+
+pyflakes:
+	pyflakes GTG
+
+# Ignoring E301 "One blank line between things within a class", since it
+# triggers false positives for normal decorator syntax.
+pep8:
+	find . -name '*.py' -print0 | xargs -0 ./scripts/pep8.py --ignore=E301
+	find . -name '*.py' -print0 | xargs -0 ./scripts/pep8.py --ignore=E301 --repeat | wc -l
+
+lint: pyflakes pep8
+
+.PHONY: lint pyflakes pep8
 
=== modified file 'scripts/codecheck.sh'
--- scripts/codecheck.sh	2009-03-31 11:04:14 +0000
+++ scripts/codecheck.sh	2009-07-13 10:41:18 +0000
@@ -37,7 +37,7 @@
 #I0011 : Locally disabling. We don't care if we disabled locally
 
 #pylint argument :
-disabled="C0324,C0103,C0301,C0111,R0914,R0903,R0915,R0904,R0912,R0201,R0913,C0323,R0902,W0102,W0232,W0105,C0321,W0401,W0142,I0011"
+disabled="C0324,C0103,C0301,C0111,R0914,R0903,R0915,R0904,R0912,R0201,R0913,C0323,R0902,W0102,W0232,W0105,C0321,W0401,W0142,I0011,C0302,W0613,W0511,W0622,R0911"
 args="--rcfile=/dev/null --include-ids=y --reports=n"
 #grepped_out="Locally disabling"
 #pylint doesn't recognize gettext _()
@@ -49,8 +49,7 @@
 
 echo "Running pyflakes"
 echo "#################"
-#pyflakes triggers a false positive with import * and with gettext _()
-pyflakes GTG|grep -v "import \*"|grep -v "undefined name '_'"
+pyflakes GTG
 
 echo "Running pylint"
 echo "#################"
@@ -61,3 +60,8 @@
 		pylint --rcfile=/dev/null --include-ids=y --reports=n --disable-msg=$disabled $i |grep -v "$grepped_out"
 	fi
 done
+
+
+echo "Running pep8"
+echo "############"
+find . -name '*.py' -print0 | xargs -0 ./scripts/pep8.py
 
=== added file 'scripts/pep8.py'
--- scripts/pep8.py	1970-01-01 00:00:00 +0000
+++ scripts/pep8.py	2009-07-13 10:12:30 +0000
@@ -0,0 +1,773 @@
+#!/usr/bin/python
+# pep8.py - Check Python source code formatting, according to PEP 8
+# Copyright (C) 2006 Johann C. Rocholl <[e-mail]>
+#
+# Permission is hereby granted, free of charge, to any person
+# obtaining a copy of this software and associated documentation files
+# (the "Software"), to deal in the Software without restriction,
+# including without limitation the rights to use, copy, modify, merge,
+# publish, distribute, sublicense, and/or sell copies of the Software,
+# and to permit persons to whom the Software is furnished to do so,
+# subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+"""
+Check Python source code formatting, according to PEP 8:
+http://www.python.org/dev/peps/pep-0008/
+
+For usage and a list of options, try this:
+$ python pep8.py -h
+
+This program and its regression test suite live here:
+http://svn.browsershots.org/trunk/devtools/pep8/
+http://trac.browsershots.org/browser/trunk/devtools/pep8/
+
+Groups of errors and warnings:
+E errors
+W warnings
+100 indentation
+200 whitespace
+300 blank lines
+400 imports
+500 line length
+600 deprecation
+
+You can add checks to this program by writing plugins. Each plugin is
+a simple function that is called for each line of source code, either
+physical or logical.
+
+Physical line:
+- Raw line of text from the input file.
+
+Logical line:
+- Multi-line statements converted to a single line.
+- Stripped left and right.
+- Contents of strings replaced with 'xxx' of same length.
+- Comments removed.
+
+The check function requests physical or logical lines by the name of
+the first argument:
+
+def maximum_line_length(physical_line)
+def extraneous_whitespace(logical_line)
+def indentation(logical_line, indent_level, state)
+
+The last example above demonstrates how check plugins can request
+additional information with extra arguments. All attributes of the
+Checker object are available. Some examples:
+
+lines: a list of the raw lines from the input file
+tokens: the tokens that contribute to this logical line
+state: dictionary for passing information across lines
+indent_level: indentation (with tabs expanded to multiples of 8)
+
+The docstring of each check function shall be the relevant part of
+text from PEP 8. It is printed if the user enables --show-pep8.
+
+"""
+
+import os
+import sys
+import re
+import time
+import inspect
+import tokenize
+from optparse import OptionParser
+from keyword import iskeyword
+from fnmatch import fnmatch
+
+__version__ = '0.2.0'
+__revision__ = '$Rev: 930 $'
+
+default_exclude = '.svn,CVS,*.pyc,*.pyo'
+
+indent_match = re.compile(r'([ \t]*)').match
+raise_comma_match = re.compile(r'raise\s+\w+\s*(,)').match
+
+operators = """
++  -  *  /  %  ^  &  |  =  <  >  >>  <<
++= -= *= /= %= ^= &= |= == <= >= >>= <<=
+!= <> :
+in is or not and
+""".split()
+
+options = None
+args = None
+
+
+##############################################################################
+# Plugins (check functions) for physical lines
+##############################################################################
+
+
+def tabs_or_spaces(physical_line, state):
+    """
+    Never mix tabs and spaces.
+
+    The most popular way of indenting Python is with spaces only.  The
+    second-most popular way is with tabs only.  Code indented with a mixture
+    of tabs and spaces should be converted to using spaces exclusively.  When
+    invoking the Python command line interpreter with the -t option, it issues
+    warnings about code that illegally mixes tabs and spaces.  When using -tt
+    these warnings become errors.  These options are highly recommended!
+    """
+    indent = indent_match(physical_line).group(1)
+    if not indent:
+        return
+    if 'indent_char' in state:
+        indent_char = state['indent_char']
+    else:
+        indent_char = indent[0]
+        state['indent_char'] = indent_char
+    for offset, char in enumerate(indent):
+        if char != indent_char:
+            return offset, "E101 indentation contains mixed spaces and tabs"
+
+
+def tabs_obsolete(physical_line):
+    """
+    For new projects, spaces-only are strongly recommended over tabs.  Most
+    editors have features that make this easy to do.
+    """
+    indent = indent_match(physical_line).group(1)
+    if indent.count('\t'):
+        return indent.index('\t'), "W191 indentation contains tabs"
+
+
+def trailing_whitespace(physical_line):
+    """
+    JCR: Trailing whitespace is superfluous.
+    """
+    physical_line = physical_line.rstrip('\n') # chr(10), newline
+    physical_line = physical_line.rstrip('\r') # chr(13), carriage return
+    physical_line = physical_line.rstrip('\x0c') # chr(12), form feed, ^L
+    stripped = physical_line.rstrip()
+    if physical_line != stripped:
+        return len(stripped), "W291 trailing whitespace"
+
+
+def maximum_line_length(physical_line):
+    """
+    Limit all lines to a maximum of 79 characters.
+
+    There are still many devices around that are limited to 80 character
+    lines; plus, limiting windows to 80 characters makes it possible to have
+    several windows side-by-side.  The default wrapping on such devices looks
+    ugly.  Therefore, please limit all lines to a maximum of 79 characters.
+    For flowing long blocks of text (docstrings or comments), limiting the
+    length to 72 characters is recommended.
+    """
+    length = len(physical_line.rstrip())
+    if length > 79:
+        return 79, "E501 line too long (%d characters)" % length
+
+
+##############################################################################
+# Plugins (check functions) for logical lines
+##############################################################################
+
+
+def blank_lines(logical_line, state, indent_level):
+    """
+    Separate top-level function and class definitions with two blank lines.
+
+    Method definitions inside a class are separated by a single blank line.
+
+    Extra blank lines may be used (sparingly) to separate groups of related
+    functions.  Blank lines may be omitted between a bunch of related
+    one-liners (e.g. a set of dummy implementations).
+
+    Use blank lines in functions, sparingly, to indicate logical sections.
+    """
+    line = logical_line
+    blank_lines = state.get('blank_lines', 0)
+    if line.startswith('def '):
+        if indent_level > 0 and blank_lines != 1:
+            return 0, "E301 expected 1 blank line, found %d" % blank_lines
+        if indent_level == 0 and blank_lines != 2:
+            return 0, "E302 expected 2 blank lines, found %d" % blank_lines
+    if blank_lines > 2:
+        return 0, "E303 too many blank lines (%d)" % blank_lines
+
+
+def extraneous_whitespace(logical_line):
+    """
+    Avoid extraneous whitespace in the following situations:
+
+    - Immediately inside parentheses, brackets or braces.
+
+    - Immediately before a comma, semicolon, or colon.
+    """
+    line = logical_line
+    for char in '([{':
+        found = line.find(char + ' ')
+        if found > -1:
+            return found + 1, "E201 whitespace after '%s'" % char
+    for char in '}])':
+        found = line.find(' ' + char)
+        if found > -1 and line[found - 1] != ',':
+            return found, "E202 whitespace before '%s'" % char
+    for char in ',;:':
+        found = line.find(' ' + char)
+        if found > -1:
+            return found, "E203 whitespace before '%s'" % char
+
+
+def indentation(logical_line, indent_level, state):
+    """
+    Use 4 spaces per indentation level.
+
+    For really old code that you don't want to mess up, you can continue to
+    use 8-space tabs.
+    """
+    line = logical_line
+    previous_level = state.get('indent_level', 0)
+    indent_expect = state.get('indent_expect', False)
+    state['indent_expect'] = line.rstrip('#').rstrip().endswith(':')
+    indent_char = state.get('indent_char', ' ')
+    state['indent_level'] = indent_level
+    if indent_char == ' ' and indent_level % 4:
+        return 0, "E111 indentation is not a multiple of four"
+    if indent_expect and indent_level <= previous_level:
+        return 0, "E112 expected an indented block"
+    if not indent_expect and indent_level > previous_level:
+        return 0, "E113 unexpected indentation"
+
+
+def whitespace_before_parameters(logical_line, tokens):
+    """
+    Avoid extraneous whitespace in the following situations:
+
+    - Immediately before the open parenthesis that starts the argument
+      list of a function call.
+
+    - Immediately before the open parenthesis that starts an indexing or
+      slicing.
+    """
+    prev_type = tokens[0][0]
+    prev_text = tokens[0][1]
+    prev_end = tokens[0][3]
+    for index in range(1, len(tokens)):
+        token_type, text, start, end, line = tokens[index]
+        if (token_type == tokenize.OP and
+            text in '([' and
+            start != prev_end and
+            prev_type == tokenize.NAME and
+            (index < 2 or tokens[index - 2][1] != 'class') and
+            (not iskeyword(prev_text))):
+            return prev_end, "E211 whitespace before '%s'" % text
+        prev_type = token_type
+        prev_text = text
+        prev_end = end
+
+
+def whitespace_around_operator(logical_line):
+    """
+    Avoid extraneous whitespace in the following situations:
+
+    - More than one space around an assignment (or other) operator to
+      align it with another.
+    """
+    line = logical_line
+    for operator in operators:
+        found = line.find('  ' + operator)
+        if found > -1:
+            return found, "E221 multiple spaces before operator"
+        found = line.find('\t' + operator)
+        if found > -1:
+            return found, "E222 tab before operator"
+
+
+def imports_on_separate_lines(logical_line):
+    """
+    Imports should usually be on separate lines.
+    """
+    line = logical_line
+    if line.startswith('import '):
+        found = line.find(',')
+        if found > -1:
+            return found, "E401 multiple imports on one line"
+
+
+def python_3000_has_key(logical_line):
+    """
+    The {}.has_key() method will be removed in the future version of
+    Python. Use the 'in' operation instead, like:
+    d = {"a": 1, "b": 2}
+    if "b" in d:
+        print d["b"]
+    """
+    pos = logical_line.find('.has_key(')
+    if pos > -1:
+        return pos, "W601 .has_key() is deprecated, use 'in'"
+
+
+def python_3000_raise_comma(logical_line):
+    """
+    When raising an exception, use "raise ValueError('message')"
+    instead of the older form "raise ValueError, 'message'".
+
+    The paren-using form is preferred because when the exception arguments
+    are long or include string formatting, you don't need to use line
+    continuation characters thanks to the containing parentheses.  The older
+    form will be removed in Python 3000.
+    """
+    match = raise_comma_match(logical_line)
+    if match:
+        return match.start(1), "W602 deprecated form of raising exception"
+
+
+##############################################################################
+# Helper functions
+##############################################################################
+
+
+def expand_indent(line):
+    """
+    Return the amount of indentation.
+    Tabs are expanded to the next multiple of 8.
+
+    >>> expand_indent('    ')
+    4
+    >>> expand_indent('\\t')
+    8
+    >>> expand_indent('    \\t')
+    8
+    >>> expand_indent('       \\t')
+    8
+    >>> expand_indent('        \\t')
+    16
+    """
+    result = 0
+    for char in line:
+        if char == '\t':
+            result = result / 8 * 8 + 8
+        elif char == ' ':
+            result += 1
+        else:
+            break
+    return result
+
+
+##############################################################################
+# Framework to run all checks
+##############################################################################
+
+
+def message(text):
+    """Print a message."""
+    # print >> sys.stderr, options.prog + ': ' + text
+    # print >> sys.stderr, text
+    print text
+
+
+def find_checks(argument_name):
+    """
+    Find all globally visible functions where the first argument name
+    starts with argument_name.
+    """
+    checks = []
+    function_type = type(find_checks)
+    for name, function in globals().iteritems():
+        if type(function) is function_type:
+            args = inspect.getargspec(function)[0]
+            if len(args) >= 1 and args[0].startswith(argument_name):
+                checks.append((name, function, args))
+    checks.sort()
+    return checks
+
+
+def mute_string(text):
+    """
+    Replace contents with 'xxx' to prevent syntax matching.
+
+    >>> mute_string('"abc"')
+    '"xxx"'
+    >>> mute_string("'''abc'''")
+    "'''xxx'''"
+    >>> mute_string("r'abc'")
+    "r'xxx'"
+    """
+    start = 1
+    end = len(text) - 1
+    # String modifiers (e.g. u or r)
+    if text.endswith('"'):
+        start += text.index('"')
+    elif text.endswith("'"):
+        start += text.index("'")
+    # Triple quotes
+    if text.endswith('"""') or text.endswith("'''"):
+        start += 2
+        end -= 2
+    return text[:start] + 'x' * (end - start) + text[end:]
+
+
+class Checker:
+    """
+    Load a Python source file, tokenize it, check coding style.
+    """
+
+    def __init__(self, filename):
+        self.filename = filename
+        self.lines = file(filename).readlines()
+        self.physical_checks = find_checks('physical_line')
+        self.logical_checks = find_checks('logical_line')
+        options.counters['physical lines'] = \
+            options.counters.get('physical lines', 0) + len(self.lines)
+
+    def readline(self):
+        """
+        Get the next line from the input buffer.
+        """
+        self.line_number += 1
+        if self.line_number > len(self.lines):
+            return ''
+        return self.lines[self.line_number - 1]
+
+    def readline_check_physical(self):
+        """
+        Check and return the next physical line. This method can be
+        used to feed tokenize.generate_tokens.
+        """
+        line = self.readline()
+        self.check_physical(line)
+        return line
+
+    def run_check(self, check, argument_names):
+        """
+        Run a check plugin.
+        """
+        arguments = []
+        for name in argument_names:
+            arguments.append(getattr(self, name))
+        return check(*arguments)
+
+    def check_physical(self, line):
+        """
+        Run all physical checks on a raw input line.
+        """
+        self.physical_line = line
+        for name, check, argument_names in self.physical_checks:
+            result = self.run_check(check, argument_names)
+            if result is not None:
+                offset, text = result
+                self.report_error(self.line_number, offset, text, check)
+
+    def build_tokens_line(self):
+        """
+        Build a logical line from tokens.
+        """
+        self.mapping = []
+        logical = []
+        length = 0
+        previous = None
+        for token in self.tokens:
+            token_type, text = token[0:2]
+            if token_type in (tokenize.COMMENT, tokenize.NL,
+                              tokenize.INDENT, tokenize.DEDENT,
+                              tokenize.NEWLINE):
+                continue
+            if token_type == tokenize.STRING:
+                text = mute_string(text)
+            if previous:
+                end_line, end = previous[3]
+                start_line, start = token[2]
+                if end_line != start_line: # different row
+                    if self.lines[end_line - 1][end - 1] not in '{[(':
+                        logical.append(' ')
+                        length += 1
+                elif end != start: # different column
+                    fill = self.lines[end_line - 1][end:start]
+                    logical.append(fill)
+                    length += len(fill)
+            self.mapping.append((length, token))
+            logical.append(text)
+            length += len(text)
+            previous = token
+        self.logical_line = ''.join(logical)
+
+    def check_logical(self):
+        """
+        Build a line from tokens and run all logical checks on it.
+        """
+        options.counters['logical lines'] = \
+            options.counters.get('logical lines', 0) + 1
+        self.build_tokens_line()
+        first_line = self.lines[self.mapping[0][1][2][0] - 1]
+        indent = first_line[:self.mapping[0][1][2][1]]
+        self.indent_level = expand_indent(indent)
+        if options.verbose >= 2:
+            print self.logical_line[:80].rstrip()
+        for name, check, argument_names in self.logical_checks:
+            if options.verbose >= 3:
+                print '   ', name
+            result = self.run_check(check, argument_names)
+            if result is not None:
+                offset, text = result
+                if type(offset) is tuple:
+                    original_number, original_offset = offset
+                else:
+                    for token_offset, token in self.mapping:
+                        if offset >= token_offset:
+                            original_number = token[2][0]
+                            original_offset = (token[2][1]
+                                               + offset - token_offset)
+                self.report_error(original_number, original_offset,
+                                  text, check)
+
+    def check_all(self):
+        """
+        Run all checks on the input file.
+        """
+        self.file_errors = 0
+        self.line_number = 0
+        self.state = {'blank_lines': 0}
+        self.tokens = []
+        parens = 0
+        for token in tokenize.generate_tokens(self.readline_check_physical):
+            # print tokenize.tok_name[token[0]], repr(token)
+            self.tokens.append(token)
+            token_type, text = token[0:2]
+            if token_type == tokenize.OP and text in '([{':
+                parens += 1
+            if token_type == tokenize.OP and text in '}])':
+                parens -= 1
+            if token_type == tokenize.NEWLINE and not parens:
+                self.check_logical()
+                self.state['blank_lines'] = 0
+                self.tokens = []
+            if token_type == tokenize.NL and len(self.tokens) == 1:
+                self.state['blank_lines'] += 1
+                self.tokens = []
+        return self.file_errors
+
+    def report_error(self, line_number, offset, text, check):
+        """
+        Report an error, according to options.
+        """
+        if options.quiet == 1 and not self.file_errors:
+            message(self.filename)
+        self.file_errors += 1
+        code = text[:4]
+        options.counters[code] = options.counters.get(code, 0) + 1
+        options.messages[code] = text[5:]
+        if options.quiet:
+            return
+        if options.testsuite:
+            base = os.path.basename(self.filename)[:4]
+            if base == code:
+                return
+            if base[0] == 'E' and code[0] == 'W':
+                return
+        if ignore_code(code):
+            return
+        if options.counters[code] == 1 or options.repeat:
+            message("%s:%s:%d: %s" %
+                    (self.filename, line_number, offset + 1, text))
+            if options.show_source:
+                line = self.lines[line_number - 1]
+                message(line.rstrip())
+                message(' ' * offset + '^')
+            if options.show_pep8:
+                message(check.__doc__.lstrip('\n').rstrip())
+
+
+def input_file(filename):
+    """
+    Run all checks on a Python source file.
+    """
+    if excluded(filename) or not filename_match(filename):
+        return {}
+    if options.verbose:
+        message('checking ' + filename)
+    options.counters['files'] = options.counters.get('files', 0) + 1
+    errors = Checker(filename).check_all()
+    if options.testsuite and not errors:
+        message("%s: %s" % (filename, "no errors found"))
+
+
+def input_dir(dirname):
+    """
+    Check all Python source files in this directory and all subdirectories.
+    """
+    dirname = dirname.rstrip('/')
+    if excluded(dirname):
+        return
+    for root, dirs, files in os.walk(dirname):
+        if options.verbose:
+            message('directory ' + root)
+        options.counters['directories'] = \
+            options.counters.get('directories', 0) + 1
+        dirs.sort()
+        for subdir in dirs:
+            if excluded(subdir):
+                dirs.remove(subdir)
+        files.sort()
+        for filename in files:
+            input_file(os.path.join(root, filename))
+
+
+def excluded(filename):
+    """
+    Check if options.exclude contains a pattern that matches filename.
+    """
+    for pattern in options.exclude:
+        if fnmatch(filename, pattern):
+            return True
+
+
+def filename_match(filename):
+    """
+    Check if options.filename contains a pattern that matches filename.
+    If options.filename is unspecified, this always returns True.
+    """
+    if not options.filename:
+        return True
+    for pattern in options.filename:
+        if fnmatch(filename, pattern):
+            return True
+
+
+def ignore_code(code):
+    """
+    Check if options.ignore contains a prefix of the error code.
+    """
+    for ignore in options.ignore:
+        if code.startswith(ignore):
+            return True
+
+
+def get_error_statistics():
+    """Get error statistics."""
+    return get_statistics("E")
+
+
+def get_warning_statistics():
+    """Get warning statistics."""
+    return get_statistics("W")
+
+
+def get_statistics(prefix=''):
+    """
+    Get statistics for message codes that start with the prefix.
+
+    prefix='' matches all errors and warnings
+    prefix='E' matches all errors
+    prefix='W' matches all warnings
+    prefix='E4' matches all errors that have to do with imports
+    """
+    stats = []
+    keys = options.messages.keys()
+    keys.sort()
+    for key in keys:
+        if key.startswith(prefix):
+            stats.append('%-7s %s %s' %
+                         (options.counters[key], key, options.messages[key]))
+    return stats
+
+
+def print_statistics(prefix=''):
+    """Print overall statistics (number of errors and warnings)."""
+    for line in get_statistics(prefix):
+        print line
+
+
+def print_benchmark(elapsed):
+    """
+    Print benchmark numbers.
+    """
+    print '%-7.2f %s' % (elapsed, 'seconds elapsed')
+    keys = ['directories', 'files',
+            'logical lines', 'physical lines']
+    for key in keys:
+        if key in options.counters:
+            print '%-7d %s per second (%d total)' % (
+                options.counters[key] / elapsed, key,
+                options.counters[key])
+
+
+def process_options(arglist=None):
+    """
+    Process options passed either via arglist or via command line args.
+    """
+    global options, args
+    usage = "%prog [options] input ..."
+    parser = OptionParser(usage)
+    parser.add_option('-v', '--verbose', default=0, action='count',
+                      help="print status messages, or debug with -vv")
+    parser.add_option('-q', '--quiet', default=0, action='count',
+                      help="report only file names, or nothing with -qq")
+    parser.add_option('--exclude', metavar='patterns', default=default_exclude,
+                      help="skip matches (default %s)" % default_exclude)
+    parser.add_option('--filename', metavar='patterns',
+                      help="only check matching files (e.g. *.py)")
+    parser.add_option('--ignore', metavar='errors', default='',
+                      help="skip errors and warnings (e.g. E4,W)")
+    parser.add_option('--repeat', action='store_true',
+                      help="show all occurrences of the same error")
+    parser.add_option('--show-source', action='store_true',
+                      help="show source code for each error")
+    parser.add_option('--show-pep8', action='store_true',
+                      help="show text of PEP 8 for each error")
+    parser.add_option('--statistics', action='store_true',
+                      help="count errors and warnings")
+    parser.add_option('--benchmark', action='store_true',
+                      help="measure processing speed")
+    parser.add_option('--testsuite', metavar='dir',
+                      help="run regression tests from dir")
+    parser.add_option('--doctest', action='store_true',
+                      help="run doctest on myself")
+    options, args = parser.parse_args(arglist)
+    if options.testsuite:
+        args.append(options.testsuite)
+    if len(args) == 0:
+        parser.error('input not specified')
+    options.prog = os.path.basename(sys.argv[0])
+    options.exclude = options.exclude.split(',')
+    for index in range(len(options.exclude)):
+        options.exclude[index] = options.exclude[index].rstrip('/')
+    if options.filename:
+        options.filename = options.filename.split(',')
+    if options.ignore:
+        options.ignore = options.ignore.split(',')
+    else:
+        options.ignore = []
+    options.counters = {}
+    options.messages = {}
+
+    return options, args
+
+def _main():
+    """
+    Parse options and run checks on Python source.
+    """
+    options, args = process_options()
+    if options.doctest:
+        import doctest
+        return doctest.testmod()
+    start_time = time.time()
+    for path in args:
+        if os.path.isdir(path):
+            input_dir(path)
+        else:
+            input_file(path)
+    elapsed = time.time() - start_time
+    if options.statistics:
+        print_statistics()
+    if options.benchmark:
+        print_benchmark(elapsed)
+
+
+if __name__ == '__main__':
+    _main()
 
=== modified file 'setup.py'
--- setup.py	2009-07-04 13:31:04 +0000
+++ setup.py	2009-07-13 09:13:22 +0000
@@ -43,7 +43,7 @@
             if file.endswith(".png") or file.endswith(".svg"):
                 dirList.append(os.path.join(root,file))
         if len(dirList)!=0:
-	    newroot = root.replace("data/","")
+            newroot = root.replace("data/","")
             fileList.append( (os.path.join(DATA_DIR,newroot),dirList) )
     return fileList