[Yum-devel] [PATCH] createrepo: compress .xml files with 'compress_type'

[Zdeněk Pavlas]

Dump metadata to uncompressed files first, then compress with 'compress_type'.
This is more flexible and saves one (two with -d) .xml.gz decompressions.
---
 createrepo/__init__.py |   45 +++++++++++++++++++--------------------------
 1 files changed, 19 insertions(+), 26 deletions(-)

diff --git a/createrepo/__init__.py b/createrepo/__init__.py
index 8d81136..6dbe992 100644
--- a/createrepo/__init__.py
+++ b/createrepo/__init__.py
@@ -435,11 +435,9 @@ class MetaDataGenerator:
 
     def _setupPrimary(self):
         # setup the primary metadata file
-        # FIXME - make this be  conf.compress_type once y-m-p is fixed
-        fpz = self.conf.primaryfile + '.' + 'gz'
         primaryfilepath = os.path.join(self.conf.outputdir, self.conf.tempdir,
-                                       fpz)
-        fo = compressOpen(primaryfilepath, 'w', 'gz')
+                                       self.conf.primaryfile)
+        fo = open(primaryfilepath, 'w')
         fo.write('<?xml version="1.0" encoding="UTF-8"?>\n')
         fo.write('<metadata xmlns="http://linux.duke.edu/metadata/common"' \
             ' xmlns:rpm="http://linux.duke.edu/metadata/rpm" packages="%s">' %
@@ -448,11 +446,9 @@ class MetaDataGenerator:
 
     def _setupFilelists(self):
         # setup the filelist file
-        # FIXME - make this be  conf.compress_type once y-m-p is fixed        
-        fpz = self.conf.filelistsfile + '.' + 'gz'
         filelistpath = os.path.join(self.conf.outputdir, self.conf.tempdir,
-                                    fpz)
-        fo = compressOpen(filelistpath, 'w', 'gz')
+                                    self.conf.filelistsfile)
+        fo = open(filelistpath, 'w')
         fo.write('<?xml version="1.0" encoding="UTF-8"?>\n')
         fo.write('<filelists xmlns="http://linux.duke.edu/metadata/filelists"' \
                  ' packages="%s">' % self.pkgcount)
@@ -460,11 +456,9 @@ class MetaDataGenerator:
 
     def _setupOther(self):
         # setup the other file
-        # FIXME - make this be  conf.compress_type once y-m-p is fixed        
-        fpz = self.conf.otherfile + '.' + 'gz'
         otherfilepath = os.path.join(self.conf.outputdir, self.conf.tempdir,
-                                     fpz)
-        fo = compressOpen(otherfilepath, 'w', 'gz')
+                                     self.conf.otherfile)
+        fo = open(otherfilepath, 'w')
         fo.write('<?xml version="1.0" encoding="UTF-8"?>\n')
         fo.write('<otherdata xmlns="http://linux.duke.edu/metadata/other"' \
                  ' packages="%s">' %
@@ -951,14 +945,15 @@ class MetaDataGenerator:
             rp = sqlitecachec.RepodataParserSqlite(repopath, repomd.repoid, None)
 
         for (rpm_file, ftype) in workfiles:
-            # when we fix y-m-p and non-gzipped xml files - then we can make this just add
-            # self.conf.compress_type
+            uncompressed = None
             if ftype in ('other', 'filelists', 'primary'):
-                rpm_file = rpm_file + '.' + 'gz'
+                uncompressed = os.path.join(repopath, rpm_file)
+                rpm_file = rpm_file + '.' + self.conf.compress_type
+                compressFile(uncompressed, os.path.join(repopath, rpm_file), self.conf.compress_type)
             elif rpm_file.find('.') != -1 and rpm_file.split('.')[-1] not in _available_compression:
                 rpm_file = rpm_file + '.' + self.conf.compress_type
             complete_path = os.path.join(repopath, rpm_file)
-            zfo = compressOpen(complete_path)
+            zfo = uncompressed and open(uncompressed) or compressOpen(complete_path)
             # This is misc.checksum() done locally so we can get the size too.
             data = misc.Checksums([sumtype])
             while data.read(zfo, 2**16):
@@ -981,18 +976,18 @@ class MetaDataGenerator:
                 if ftype == 'primary':
                     #FIXME - in theory some sort of try/except  here
                     # TypeError appears to be raised, sometimes :(
-                    rp.getPrimary(complete_path, csum)
+                    rp.getPrimary(uncompressed, csum)
 
                 elif ftype == 'filelists':
                     #FIXME and here
-                    rp.getFilelists(complete_path, csum)
+                    rp.getFilelists(uncompressed, csum)
 
                 elif ftype == 'other':
                     #FIXME and here
-                    rp.getOtherdata(complete_path, csum)
+                    rp.getOtherdata(uncompressed, csum)
 
                 if ftype in ['primary', 'filelists', 'other']:
-                    tmp_result_name = '%s.xml.gz.sqlite' % ftype
+                    tmp_result_name = '%s.xml.sqlite' % ftype
                     tmp_result_path = os.path.join(repopath, tmp_result_name)
                     good_name = '%s.sqlite' % ftype
                     resultpath = os.path.join(repopath, good_name)
@@ -1055,7 +1050,9 @@ class MetaDataGenerator:
                         self.callback.log("Ending %s db creation: %s" % (ftype,
                                                                   time.ctime()))
                     repomd.repoData[data.type] = data
-                    
+            if ftype in ['primary', 'filelists', 'other']:
+                os.unlink(uncompressed)
+
             data = RepoData()
             data.type = ftype
             data.checksum = (sumtype, csum)
@@ -1065,11 +1062,7 @@ class MetaDataGenerator:
             data.openchecksum = (sumtype, uncsum)
 
             if self.conf.unique_md_filenames:
-                if ftype in ('primary', 'filelists', 'other'):
-                    compress = 'gz'
-                else:
-                    compress = self.conf.compress_type
-                
+                compress = self.conf.compress_type
                 main_name = '.'.join(rpm_file.split('.')[:-1])
                 res_file = '%s-%s.%s' % (csum, main_name, compress)
                 orig_file = os.path.join(repopath, rpm_file)
-- 
1.7.4.4