tools/glusterfind: GFID to Path conversion using Changelog

Records fop information collected from Changelogs in sqlite database.
This is only working database, not required after processing.

After post processing, output file is generated by reading these
database files.

This is applicable only in incremental run, When a changelog is
parsed, all the details are saved in Db. GFID to Path is converted
to those files for which information is available in Changelogs.

For all the failed cases, it tries to convert to Path using Pgfid,
if not found GFID to Path is done using find.

BUG: 1201284
Change-Id: I53f168860dae15a0149004835e67f97aebd822be
Signed-off-by: Aravinda VK <avishwan@redhat.com>
Reviewed-on: http://review.gluster.org/10463
Reviewed-by: Kotresh HR <khiremat@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>

1 files changed, 17 insertions, 8 deletions

diff --git a/tools/glusterfind/src/utils.py b/tools/glusterfind/src/utils.py
index aea9a9dc82d..cda5ea6378e 100644
--- a/tools/glusterfind/src/utils.py
+++ b/tools/glusterfind/src/utils.py
@@ -24,6 +24,13 @@ ParseError = etree.ParseError if hasattr(etree, 'ParseError') else SyntaxError
 cache_data = {}
 
 
+class RecordType(object):
+    NEW = "NEW"
+    MODIFY = "MODIFY"
+    RENAME = "RENAME"
+    DELETE = "DELETE"
+
+
 def cache_output(func):
     def wrapper(*args, **kwargs):
         global cache_data
@@ -46,8 +53,10 @@ def find(path, callback_func=lambda x: True, filter_func=lambda x: True,
     if path in ignore_dirs:
         return
 
-    if filter_func(path):
-        callback_func(path)
+    # Capture filter_func output and pass it to callback function
+    filter_result = filter_func(path)
+    if filter_result is not None:
+        callback_func(path, filter_result)
 
     for p in os.listdir(path):
         full_path = os.path.join(path, p)
@@ -56,11 +65,13 @@ def find(path, callback_func=lambda x: True, filter_func=lambda x: True,
             if subdirs_crawl:
                 find(full_path, callback_func, filter_func, ignore_dirs)
             else:
-                if filter_func(full_path):
-                    callback_func(full_path)
+                filter_result = filter_func(full_path)
+                if filter_result is not None:
+                    callback_func(full_path, filter_result)
         else:
-            if filter_func(full_path):
-                callback_func(full_path)
+            filter_result = filter_func(full_path)
+            if filter_result is not None:
+                callback_func(full_path, filter_result)
 
 
 def output_write(f, path, prefix=".", encode=False):
@@ -215,5 +226,3 @@ def get_changelog_rollover_time(volumename):
         return int(tree.find('volGetopts/Value').text)
     except ParseError:
         return DEFAULT_CHANGELOG_INTERVAL
-
-