[PATCHv2] lib/bb: Add BB_SIGNATURE_LOCAL_DIRS_EXCLUDE to speed-up taskhash on directories

["Aníbal Limón" <anibal.limon@linaro.org>]

The new BB_SIGNATURE_LOCAL_DIRS_EXCLUDE allows you to specify a list
of directories to exclude when making taskhash, our specific case
is using SRC_URI that points local VCS directory.

Use bb.fetch.module to set default to: "CVS .bzr .git .hg .osc .p4 .repo .svn"

Signed-off-by: Aníbal Limón <anibal.limon@linaro.org>
---
 lib/bb/checksum.py        | 5 +++--
 lib/bb/fetch2/__init__.py | 4 ++--
 lib/bb/siggen.py          | 5 +++--
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/lib/bb/checksum.py b/lib/bb/checksum.py
index 5bc8a8fc..677020f4 100644
--- a/lib/bb/checksum.py
+++ b/lib/bb/checksum.py
@@ -74,7 +74,7 @@ class FileChecksumCache(MultiProcessCache):
             else:
                 dest[0][h] = source[0][h]
 
-    def get_checksums(self, filelist, pn):
+    def get_checksums(self, filelist, pn, localdirsexclude):
         """Get checksums for a list of files"""
 
         def checksum_file(f):
@@ -90,7 +90,8 @@ class FileChecksumCache(MultiProcessCache):
             if pth == "/":
                 bb.fatal("Refusing to checksum /")
             dirchecksums = []
-            for root, dirs, files in os.walk(pth):
+            for root, dirs, files in os.walk(pth, topdown=True):
+                [dirs.remove(d) for d in list(dirs) if d in localdirsexclude]
                 for name in files:
                     fullpth = os.path.join(root, name)
                     checksum = checksum_file(fullpth)
diff --git a/lib/bb/fetch2/__init__.py b/lib/bb/fetch2/__init__.py
index 07de6c26..731c1608 100644
--- a/lib/bb/fetch2/__init__.py
+++ b/lib/bb/fetch2/__init__.py
@@ -1197,14 +1197,14 @@ def get_checksum_file_list(d):
 
     return " ".join(filelist)
 
-def get_file_checksums(filelist, pn):
+def get_file_checksums(filelist, pn, localdirsexclude):
     """Get a list of the checksums for a list of local files
 
     Returns the checksums for a list of local files, caching the results as
     it proceeds
 
     """
-    return _checksum_cache.get_checksums(filelist, pn)
+    return _checksum_cache.get_checksums(filelist, pn, localdirsexclude)
 
 
 class FetchData(object):
diff --git a/lib/bb/siggen.py b/lib/bb/siggen.py
index a4bb1ff7..2445a340 100644
--- a/lib/bb/siggen.py
+++ b/lib/bb/siggen.py
@@ -123,6 +123,7 @@ class SignatureGeneratorBasic(SignatureGenerator):
 
         self.unihash_cache = bb.cache.SimpleCache("1")
         self.unitaskhashes = self.unihash_cache.init_cache(data, "bb_unihashes.dat", {})
+        self.localdirsexclude = (data.getVar("BB_SIGNATURE_LOCAL_DIRS_EXCLUDE") or "CVS .bzr .git .hg .osc .p4 .repo .svn").split()
 
     def init_rundepcheck(self, data):
         self.taskwhitelist = data.getVar("BB_HASHTASK_WHITELIST") or None
@@ -221,9 +222,9 @@ class SignatureGeneratorBasic(SignatureGenerator):
 
         if task in dataCache.file_checksums[fn]:
             if self.checksum_cache:
-                checksums = self.checksum_cache.get_checksums(dataCache.file_checksums[fn][task], recipename)
+                checksums = self.checksum_cache.get_checksums(dataCache.file_checksums[fn][task], recipename, self.localdirsexclude)
             else:
-                checksums = bb.fetch2.get_file_checksums(dataCache.file_checksums[fn][task], recipename)
+                checksums = bb.fetch2.get_file_checksums(dataCache.file_checksums[fn][task], recipename, self.localdirsexclude)
             for (f,cs) in checksums:
                 self.file_checksum_values[tid].append((f,cs))
                 if cs:
-- 
2.24.0