From 8887b7f0579e151765f2d2616b797d7ab48a8990 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Wed, 27 Apr 2011 14:19:25 -0600
Subject: [PATCH] CHM Input: Store extracted files in the input/ sub dir for
 easy debugging when --debug-pipeline is specified

---
 src/calibre/ebooks/chm/input.py          | 12 ++++++++----
 src/calibre/ebooks/chm/reader.py         |  9 ++++++---
 src/calibre/ebooks/conversion/plumber.py |  3 ++-
 3 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/src/calibre/ebooks/chm/input.py b/src/calibre/ebooks/chm/input.py
index fce07c2359..b5074e8a72 100644
--- a/src/calibre/ebooks/chm/input.py
+++ b/src/calibre/ebooks/chm/input.py
@@ -19,12 +19,12 @@ class CHMInput(InputFormatPlugin):
     description = 'Convert CHM files to OEB'
     file_types  = set(['chm'])
 
-    def _chmtohtml(self, output_dir, chm_path, no_images, log):
+    def _chmtohtml(self, output_dir, chm_path, no_images, log, debug_dump=False):
         from calibre.ebooks.chm.reader import CHMReader
         log.debug('Opening CHM file')
         rdr = CHMReader(chm_path, log, self.opts)
         log.debug('Extracting CHM to %s' % output_dir)
-        rdr.extract_content(output_dir)
+        rdr.extract_content(output_dir, debug_dump=debug_dump)
         self._chm_reader = rdr
         return rdr.hhc_path
 
@@ -47,7 +47,12 @@ class CHMInput(InputFormatPlugin):
             stream.close()
             log.debug('tdir=%s' % tdir)
             log.debug('stream.name=%s' % stream.name)
-            mainname = self._chmtohtml(tdir, chm_name, no_images, log)
+            debug_dump = False
+            odi = options.debug_pipeline
+            if odi:
+                debug_dump = os.path.join(odi, 'input')
+            mainname = self._chmtohtml(tdir, chm_name, no_images, log,
+                    debug_dump=debug_dump)
             mainpath = os.path.join(tdir, mainname)
 
             metadata = get_metadata_from_reader(self._chm_reader)
@@ -56,7 +61,6 @@ class CHMInput(InputFormatPlugin):
             #from calibre import ipython
             #ipython()
 
-            odi = options.debug_pipeline
             options.debug_pipeline = None
             options.input_encoding = 'utf-8'
             # try a custom conversion:
diff --git a/src/calibre/ebooks/chm/reader.py b/src/calibre/ebooks/chm/reader.py
index 24814a34f9..5f23ad0241 100644
--- a/src/calibre/ebooks/chm/reader.py
+++ b/src/calibre/ebooks/chm/reader.py
@@ -97,7 +97,7 @@ class CHMReader(CHMFile):
             raise CHMError("'%s' is zero bytes in length!"%(path,))
         return data
 
-    def ExtractFiles(self, output_dir=os.getcwdu()):
+    def ExtractFiles(self, output_dir=os.getcwdu(), debug_dump=False):
         html_files = set([])
         for path in self.Contents():
             lpath = os.path.join(output_dir, path)
@@ -123,6 +123,9 @@ class CHMReader(CHMFile):
                     self.log.warn('%r filename too long, skipping'%path)
                     continue
                 raise
+        if debug_dump:
+            import shutil
+            shutil.copytree(output_dir, os.path.join(debug_dump, 'debug_dump'))
         for lpath in html_files:
             with open(lpath, 'r+b') as f:
                 data = f.read()
@@ -249,8 +252,8 @@ class CHMReader(CHMFile):
         if not os.path.isdir(dir):
             os.makedirs(dir)
 
-    def extract_content(self, output_dir=os.getcwdu()):
-        self.ExtractFiles(output_dir=output_dir)
+    def extract_content(self, output_dir=os.getcwdu(), debug_dump=False):
+        self.ExtractFiles(output_dir=output_dir, debug_dump=debug_dump)
 
 
 
diff --git a/src/calibre/ebooks/conversion/plumber.py b/src/calibre/ebooks/conversion/plumber.py
index 96ea3e5884..3eb59a21b9 100644
--- a/src/calibre/ebooks/conversion/plumber.py
+++ b/src/calibre/ebooks/conversion/plumber.py
@@ -854,7 +854,8 @@ OptionRecommendation(name='sr3_replace',
         if isinstance(ret, basestring):
             shutil.copytree(output_dir, out_dir)
         else:
-            os.makedirs(out_dir)
+            if not os.path.exists(out_dir):
+                os.makedirs(out_dir)
             self.dump_oeb(ret, out_dir)
         if self.input_fmt == 'recipe':
             zf = ZipFile(os.path.join(self.opts.debug_pipeline,