Better support of PDF/PS docs

MANIFEST.in

@@ -0,0 +1 @@
+include kittengroomer/data/*

README.rst

@@ -0,0 +1 @@
+README.md

bin/generic.py

@@ -19,7 +19,7 @@ SEVENZ = '/usr/bin/7z'
 # Prepare application/<subtype>
 mimes_office = ['msword', 'vnd.openxmlformats-officedocument.', 'vnd.ms-',
                 'vnd.oasis.opendocument']
-mimes_pdf = ['pdf']
+mimes_pdf = ['pdf', 'postscript']
 mimes_xml = ['xml']
 mimes_ms = ['x-dosexec']
 mimes_compressed = ['zip', 'x-rar', 'x-bzip2', 'x-lzip', 'x-lzma', 'x-lzop',
@@ -49,8 +49,12 @@ class File(FileBase):
         mimetype = magic.from_file(src_path, mime=True).decode("utf-8")
         self.main_type, self.sub_type = mimetype.split('/')
         a, self.extension = os.path.splitext(src_path)
+        self.is_recursive = False
 
         self.log_details.update({'maintype': self.main_type, 'subtype': self.sub_type, 'extension': self.extension})
+        # If the mimetype matches as text/*, it will be sent to LibreOffice, no need to cross check the mime/ext
+        if self.main_type == 'text':
+            return
 
         # Check correlation known extension => actual mime type
         if propertype.get(self.extension) is not None:
@@ -77,8 +81,6 @@ class File(FileBase):
             # there are no known extensions associated to this mimetype.
             pass
 
-        self.is_recursive = False
-
 
 class KittenGroomer(KittenGroomerBase):
 
@@ -253,9 +255,13 @@ class KittenGroomer(KittenGroomerBase):
         tmpdir = os.path.join(dst_dir, 'temp')
         tmppath = os.path.join(tmpdir, filename)
         self._safe_mkdir(tmpdir)
-        gs_command = '{} -dPDFA -dBATCH -dNOPAUSE -sDEVICE=pdfwrite -sOutputFile={} {}'.format(
+        # The magic comes from here: http://svn.ghostscript.com/ghostscript/trunk/gs/doc/Ps2pdf.htm#PDFA
-            GS, tmppath, self.cur_file.src_path)
+        curdir = os.getcwd()
+        os.chdir(self.ressources_path)
+        gs_command = '{} -dPDFA -dBATCH -dNOPAUSE -dNOOUTERSAVE -sProcessColorModel=DeviceCMYK -sDEVICE=pdfwrite -sPDFACompatibilityPolicy=1 -sOutputFile={} PDFA_def.ps {}'.format(
+            GS, os.path.join(curdir, tmppath), os.path.join(curdir, self.cur_file.src_path))
         self._run_process(gs_command)
+        os.chdir(curdir)
         self._pdfa(tmppath)
         self._safe_rmtree(tmpdir)
 

kittengroomer/data/PDFA_def.ps

@@ -0,0 +1,40 @@
+%!
+% This is a sample prefix file for creating a PDF/A document.
+% Feel free to modify entries marked with "Customize".
+% This assumes an ICC profile to reside in the file (ISO Coated sb.icc),
+% unless the user modifies the corresponding line below.
+
+% Define entries in the document Info dictionary :
+/ICCProfile (srgb.icc) % Customise
+def
+
+[ /Title (Title)       % Customise
+  /DOCINFO pdfmark
+
+% Define an ICC profile :
+
+[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
+[{icc_PDFA}
+<<
+  /N currentpagedevice /ProcessColorModel known {
+    currentpagedevice /ProcessColorModel get dup /DeviceGray eq
+    {pop 1} {
+      /DeviceRGB eq
+      {3}{4} ifelse
+    } ifelse
+  } {
+    (ERROR, unable to determine ProcessColorModel) == flush
+  } ifelse
+>> /PUT pdfmark
+[{icc_PDFA} ICCProfile (r) file /PUT pdfmark
+
+% Define the output intent dictionary :
+
+[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
+[{OutputIntent_PDFA} <<
+  /Type /OutputIntent             % Must be so (the standard requires).
+  /S /GTS_PDFA1                   % Must be so (the standard requires).
+  /DestOutputProfile {icc_PDFA}            % Must be so (see above).
+  /OutputConditionIdentifier (sRGB)      % Customize
+>> /PUT pdfmark
+[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark

kittengroomer/helpers.py

@@ -94,6 +94,8 @@ class KittenGroomerBase(object):
 
         quickSetup(file=self.log_processing)
         self.log_name = log.name('files')
+        self.ressources_path = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'data')
+        os.environ["PATH"] += os.pathsep + self.ressources_path
 
         self.cur_file = None
 
@@ -113,12 +115,16 @@ class KittenGroomerBase(object):
         if not os.path.exists(directory):
             os.makedirs(directory)
 
-    def _safe_copy(self):
+    def _safe_copy(self, src=None, dst=None):
         ''' Copy a file and create directory if needed '''
+        if src is None:
+            src = self.cur_file.src_path
+        if dst is None:
+            dst = self.cur_file.dst_path
         try:
-            dst_path, filename = os.path.split(self.cur_file.dst_path)
+            dst_path, filename = os.path.split(dst)
             self._safe_mkdir(dst_path)
-            shutil.copy(self.cur_file.src_path, self.cur_file.dst_path)
+            shutil.copy(src, dst)
             return True
         except Exception as e:
             # TODO: Logfile

setup.py

@@ -12,6 +12,8 @@ setup(
     description='Standalone CIRCLean/KittenGroomer code.',
     packages=['kittengroomer'],
     scripts=['bin/generic.py', 'bin/pier9.py'],
+    include_package_data = True,
+    package_data = {'data': ['PDFA_def.ps','srgb.icc']},
     classifiers=[
         'License :: OSI Approved :: BSD License',
         'Development Status :: 5 - Production/Stable',