bitbake: implement checksums for local files in SRC_URI

Gathers a list of paths to have checksums calculated at parse time, and
processes these when calculating task hashes. Checksums are cached with
the file's current mtime. Thus, changing any local file in SRC_URI will
now cause the do_fetch taskhash to change, thus forcing a rebuild.

This change adds very roughly about an 8% increase in parse time (a few
seconds) and maybe a few seconds during runqueue generation, so a fairly
moderate performance hit.

Note that since paths are resolved at parse time, this will not force
a rebuild when files are introduced which would cause that resolved path
to be different - for example, where a machine-specific version of a file
was added without otherwise changing the recipe. This will need to be
handled in a future update.

Code to hook this into the signature generator was courtesy of
Richard Purdie <richard.purdie@linuxfoundation.org>.

Implements [YOCTO #2044].

(Bitbake rev: c993b7c457f8b7776e8a5dff253bfa0724bc2cae)

Signed-off-by: Paul Eggleton <paul.eggleton@linux.intel.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

1 files changed, 85 insertions, 0 deletions

diff --git a/bitbake/lib/bb/fetch2/__init__.py b/bitbake/lib/bb/fetch2/__init__.py
index 0b976c4079..d4b6c3ec39 100644
--- a/bitbake/lib/bb/fetch2/__init__.py
+++ b/bitbake/lib/bb/fetch2/__init__.py
@@ -8,6 +8,7 @@ BitBake build tools.
 """
 
 # Copyright (C) 2003, 2004  Chris Larson
+# Copyright (C) 2012  Intel Corporation
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 2 as
@@ -30,9 +31,11 @@ import os, re
 import logging
 import urllib
 import bb.persist_data, bb.utils
+import bb.checksum
 from bb import data
 
 __version__ = "2"
+_checksum_cache = bb.checksum.FileChecksumCache()
 
 logger = logging.getLogger("BitBake.Fetcher")
 
@@ -233,10 +236,18 @@ def fetcher_init(d):
     else:
         raise FetchError("Invalid SRCREV cache policy of: %s" % srcrev_policy)
 
+    _checksum_cache.init_cache(d)
+
     for m in methods:
         if hasattr(m, "init"):
             m.init(d)
 
+def fetcher_parse_save(d):
+    _checksum_cache.save_extras(d)
+
+def fetcher_parse_done(d):
+    _checksum_cache.save_merge(d)
+
 def fetcher_compare_revisions(d):
     """
     Compare the revisions in the persistant cache with current values and
@@ -553,6 +564,80 @@ def srcrev_internal_helper(ud, d, name):
 
     return rev
 
+
+def get_checksum_file_list(d):
+    """ Get a list of files checksum in SRC_URI
+
+    Returns the all resolved local path of all local file entries in
+    SRC_URI as a space-separated string
+    """
+    fetch = Fetch([], d)
+
+    dl_dir = d.getVar('DL_DIR', True)
+    filelist = []
+    for u in fetch.urls:
+        ud = fetch.ud[u]
+
+        if isinstance(ud.method, local.Local):
+            ud.setup_localpath(d)
+            f = ud.localpath
+            if f.startswith(dl_dir):
+                # The local fetcher's behaviour is to return a path under DL_DIR if it couldn't find the file anywhere else
+                if os.path.exists(f):
+                    bb.warn("Getting checksum for %s SRC_URI entry %s: file not found except in DL_DIR" % (d.getVar('PN', True), os.path.basename(f)))
+                else:
+                    bb.warn("Unable to get checksum for %s SRC_URI entry %s: file could not be found" % (d.getVar('PN', True), os.path.basename(f)))
+                    continue
+            filelist.append(f)
+
+    return " ".join(filelist)
+
+
+def get_file_checksums(filelist, pn):
+    """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
+
+    """
+
+    def checksum_file(f):
+        try:
+            checksum = _checksum_cache.get_checksum(f)
+        except OSError as e:
+            import traceback
+            bb.warn("Unable to get checksum for %s SRC_URI entry %s: %s" % (pn, os.path.basename(f), e))
+            return None
+        return checksum
+
+    checksums = []
+    for pth in filelist.split():
+        checksum = None
+        if '*' in pth:
+            # Handle globs
+            import glob
+            for f in glob.glob(pth):
+                checksum = checksum_file(f)
+                if checksum:
+                    checksums.append((f, checksum))
+        elif os.path.isdir(pth):
+            # Handle directories
+            for root, dirs, files in os.walk(pth):
+                for name in files:
+                    fullpth = os.path.join(root, name)
+                    checksum = checksum_file(fullpth)
+                    if checksum:
+                        checksums.append((fullpth, checksum))
+        else:
+            checksum = checksum_file(pth)
+
+        if checksum:
+            checksums.append((pth, checksum))
+
+    checksums.sort()
+    return checksums
+
+
 class FetchData(object):
     """
     A class which represents the fetcher state for a given URI.