Simple CMS as Anwiki replacement

sitescripts/web/bin/generate_static_pages.py

Index: sitescripts/web/bin/generate_static_pages.py
===================================================================
new file mode 100644
--- /dev/null
+++ b/sitescripts/web/bin/generate_static_pages.py
@@ -0,0 +1,89 @@
+# coding: utf-8
+
+# This file is part of the Adblock Plus web scripts,
+# Copyright (C) 2006-2013 Eyeo GmbH
+#
+# Adblock Plus is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 3 as
+# published by the Free Software Foundation.
+#
+# Adblock Plus is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
+
+import sys, os, re, codecs
+from ...utils import setupStderr
+from ..utils import process_page
+from ..sources import MercurialSource
+
+def generate_pages(repo, output_dir):
+  known_files = set()
+
+  def write_file(path_parts, contents, binary=False):
+    encoding = None if binary else "utf-8"
+    outfile = os.path.join(output_dir, *path_parts)
+    if outfile in known_files:
+      print >>sys.stderr, "Warning: File %s has multiple sources" % outfile
+      return
+    known_files.add(outfile)
+
+    if os.path.exists(outfile):
+      with codecs.open(outfile, "rb", encoding=encoding) as handle:
+        if handle.read() == contents:
+          return
+
+    try:
+      os.makedirs(os.path.dirname(outfile))
+    except OSError:
+      pass

[Sebastian Noack, 2013/10/29 11:04:17]

I would check if we got EEXIST here and only then fail silently and otherwise
re-raise the error. Otherwise for example when you don't have permissions to
create the directory, the code below will fail because of the directory doesn't
exist, which is misleading.

try:
  os.makedirs(os.path.dirname(outfile))
except OSError, e:
  if e.errno != errno.EEXIST:
    raise

+
+    with codecs.open(outfile, "wb", encoding=encoding) as handle:
+      handle.write(contents)
+
+  with MercurialSource(repo) as source:
+    locales = list(source.list_locales())
+    for page, format in source.list_pages():
+      for locale in locales:
+        if source.has_locale(locale, page):
+          pagedata = process_page(source, locale, page, format)
+
+          # Make sure links to static files are versioned
+          pagedata = re.sub(r'(<script\s[^<>]*\bsrc="/[^"<>]+)', r"\1?%s" % source.version, pagedata)

[Sebastian Noack, 2013/10/29 11:04:17]

When you inject text into regular expressions always use re.escape().

[Wladimir Palant, 2013/11/04 09:49:21]

I'm not injecting into a regular expression here, it's the replacement term.
Using re.escape() can be fatal here, consider the following:

    re.sub("(a)", r"\1%s" % re.escape("$"), "abcd")

Given that source.version is known to be alphanumerical we can skip escaping
here. I've fixed this in a some other places however.

[Sebastian Noack, 2013/11/04 13:28:18]

Yes, you are right.

+          pagedata = re.sub(r'(<link\s[^<>]*\bhref="/[^"<>]+)', r"\1?%s" % source.version, pagedata)
+          pagedata = re.sub(r'(<img\s[^<>]*\bsrc="/[^"<>]+)', r"\1?%s" % source.version, pagedata)
+
+          write_file([locale] + page.split("/"), pagedata)
+
+    for filename in source.list_localizable_files():
+      for locale in locales:
+        if source.has_localizable_file(locale, filename):
+          filedata = source.read_localizable_file(locale, filename)
+          write_file([locale] + filename.split("/"), filedata, binary=True)
+
+    for filename in source.list_static():
+      write_file(filename.split("/"), source.read_static(filename), binary=True)
+
+  def remove_unknown(dir):
+    files = os.listdir(dir)
+    for filename in files:
+      path = os.path.join(dir, filename)
+      if os.path.isfile(path) and path not in known_files:
+        os.remove(path)
+      elif os.path.isdir(path):
+        remove_unknown(path)
+        if not os.listdir(path):
+          os.rmdir(path)

[Sebastian Noack, 2013/10/29 11:04:17]

You might want to remove directories recursively. So that when a/b/c.html is
removed and there aren't any other files within a will be removed too, instead
of removing only a/b.

[Wladimir Palant, 2013/11/04 09:49:21]

We are already removing directories recursively. remove_unknown("foo/a/b") will
remove foo/a/b/c.html and then return to remove_unknown("foo/a") that will
remove foo/a/b as an empty directory. It will then return to
remove_unknown("foo") which will remove foo/a. The top-level directory is never
removed which is intended.

[Sebastian Noack, 2013/11/04 13:28:18]

You are right.

+  remove_unknown(output_dir)
+
+if __name__ == "__main__":
+  setupStderr()
+  if len(sys.argv) < 3:
+    print >>sys.stderr, "Usage: %s source_repository output_dir" % sys.argv[0]
+    sys.exit(1)
+
+  repo, output_dir = sys.argv[1:3]
+  generate_pages(repo, output_dir)