buildhistory improvements

index 8493da4..30c2c08 100755
@@ -2,7 +2,7 @@
 
 # Report significant differences in the buildhistory repository since a specific revision
 #
-# Copyright (C) 2012 Intel Corporation
+# Copyright (C) 2013 Intel Corporation
 # Author: Paul Eggleton <[email protected]>
 
 import sys

@@ -18,10 +18,10 @@ except ImportError:
 
 def main():
     if LooseVersion(git.__version__) < '0.3.1':
-        print("Version of GitPython is too old, please install GitPython (python-git) 0.3.1 or later in order to use this script")
+        sys.stderr.write("Version of GitPython is too old, please install GitPython (python-git) 0.3.1 or later in order to use this script\n")
         sys.exit(1)
 
-    if (len(sys.argv) < 3):
+    if len(sys.argv) < 3 or '--help' in sys.argv:
         print("Report significant differences in the buildhistory repository")
         print("Syntax: %s <buildhistory-path> <since-revision> [to-revision]" % os.path.basename(sys.argv[0]))
         print("If to-revision is not specified, it defaults to HEAD")

@@ -41,17 +41,29 @@ def main():
                 bitbakepath = os.path.abspath(os.path.join(pth, '..'))
                 break
         if not bitbakepath:
-            print("Unable to find bitbake by searching parent directory of this script or PATH")
+            sys.stderr.write("Unable to find bitbake by searching parent directory of this script or PATH\n")
             sys.exit(1)
 
     sys.path[0:0] = [newpath, bitbakepath + '/lib']
     import oe.buildhistory_analysis
 
+    buildhistory_dir = sys.argv[1]
+    if not os.path.exists(buildhistory_dir):
+        sys.stderr.write('Specified buildhistory directory "%s" does not exist\n' % buildhistory_dir)
+        sys.exit(1)
+
     if len(sys.argv) > 3:
         torev = sys.argv[3]
     else:
         torev = 'HEAD'
-    changes = oe.buildhistory_analysis.process_changes(sys.argv[1], sys.argv[2], torev)
+
+    import gitdb
+    try:
+        changes = oe.buildhistory_analysis.process_changes(buildhistory_dir, sys.argv[2], torev)
+    except gitdb.exc.BadObject as e:
+        sys.stderr.write('Specified git revision "%s" is not valid\n' % e.args[0])
+        sys.exit(1)
+
     for chg in changes:
         print('%s' % chg)
 

index 8efd41c..3b6ce99 100644
@@ -12,6 +12,7 @@ BUILDHISTORY_DIR ?= "${TOPDIR}/buildhistory"
 BUILDHISTORY_DIR_IMAGE = "${BUILDHISTORY_DIR}/images/${MACHINE_ARCH}/${TCLIBC}/${IMAGE_BASENAME}"
 BUILDHISTORY_DIR_PACKAGE = "${BUILDHISTORY_DIR}/packages/${MULTIMACH_TARGET_SYS}/${PN}"
 BUILDHISTORY_DIR_SDK = "${BUILDHISTORY_DIR}/sdk/${SDK_NAME}"
+BUILDHISTORY_IMAGE_FILES ?= "/etc/passwd /etc/group"
 BUILDHISTORY_COMMIT ?= "0"
 BUILDHISTORY_COMMIT_AUTHOR ?= "buildhistory <buildhistory@${DISTRO}>"
 BUILDHISTORY_PUSH_REPO ?= ""

@@ -396,6 +397,15 @@ buildhistory_get_imageinfo() {
 
 	buildhistory_list_files ${IMAGE_ROOTFS} ${BUILDHISTORY_DIR_IMAGE}/files-in-image.txt
 
+	# Collect files requested in BUILDHISTORY_IMAGE_FILES
+	rm -rf ${BUILDHISTORY_DIR_IMAGE}/image-files
+	for f in ${BUILDHISTORY_IMAGE_FILES}; do
+		if [ -f ${IMAGE_ROOTFS}/$f ] ; then
+			mkdir -p ${BUILDHISTORY_DIR_IMAGE}/image-files/`dirname $f`
+			cp ${IMAGE_ROOTFS}/$f ${BUILDHISTORY_DIR_IMAGE}/image-files/$f
+		fi
+	done
+
 	# Record some machine-readable meta-information about the image
 	printf ""  > ${BUILDHISTORY_DIR_IMAGE}/image-info.txt
 	cat >> ${BUILDHISTORY_DIR_IMAGE}/image-info.txt <<END

index 2306bcb..86b5a12 100644
@@ -52,7 +52,10 @@ class ChangeRecord:
 
     def _str_internal(self, outer):
         if outer:
-            prefix = '%s: ' % self.path
+            if '/image-files/' in self.path:
+                prefix = '%s: ' % self.path.split('/image-files/')[0]
+            else:
+                prefix = '%s: ' % self.path
         else:
             prefix = ''
 

@@ -107,16 +110,21 @@ class ChangeRecord:
             diff = difflib.unified_diff(alines, blines, self.fieldname, self.fieldname, lineterm='')
             out += '\n  '.join(list(diff)[2:])
             out += '\n  --'
-        elif self.fieldname in img_monitor_files:
-            if outer:
-                prefix = 'Changes to %s ' % self.path
-            out = '(%s):\n  ' % self.fieldname
+        elif self.fieldname in img_monitor_files or '/image-files/' in self.path:
+            fieldname = self.fieldname
+            if '/image-files/' in self.path:
+                fieldname = os.path.join('/' + self.path.split('/image-files/')[1], self.fieldname)
+                out = 'Changes to %s:\n  ' % fieldname
+            else:
+                if outer:
+                    prefix = 'Changes to %s ' % self.path
+                out = '(%s):\n  ' % self.fieldname
             if self.filechanges:
                 out += '\n  '.join(['%s' % i for i in self.filechanges])
             else:
                 alines = self.oldvalue.splitlines()
                 blines = self.newvalue.splitlines()
-                diff = difflib.unified_diff(alines, blines, self.fieldname, self.fieldname, lineterm='')
+                diff = difflib.unified_diff(alines, blines, fieldname, fieldname, lineterm='')
                 out += '\n  '.join(list(diff))
                 out += '\n  --'
         else:

@@ -393,6 +401,9 @@ def process_changes(repopath, revision1, revision2 = 'HEAD', report_all = False)
                     changes.append(chg)
             elif filename == 'image-info.txt':
                 changes.extend(compare_dict_blobs(path, d.a_blob, d.b_blob, report_all))
+            elif '/image-files/' in path:
+                chg = ChangeRecord(path, filename, d.a_blob.data_stream.read(), d.b_blob.data_stream.read(), True)
+                changes.append(chg)
 
     # Look for added preinst/postinst/prerm/postrm
     # (without reporting newly added recipes)