classes/reproducible: Move to library code

Moves most of the python code used for dealing with the source date
epoch to library code.

(From OE-Core rev: bb957547fbd3f6670220706642b49fee560c6b75)

Signed-off-by: Joshua Watt <JPEWhacker@gmail.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
(cherry picked from commit a7ede90955bc0c8bec1cbb3cab498ef2583b2f4e)
Signed-off-by: Steve Sakoman <steve@sakoman.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

1 files changed, 95 insertions, 0 deletions

diff --git a/meta/lib/oe/reproducible.py b/meta/lib/oe/reproducible.py
new file mode 100644
index 0000000000..f80a85ddef
--- /dev/null
+++ b/meta/lib/oe/reproducible.py
@@ -0,0 +1,95 @@
+#
+# SPDX-License-Identifier: GPL-2.0-only
+#
+import os
+import subprocess
+import bb
+
+def get_source_date_epoch_from_known_files(d, sourcedir):
+    source_date_epoch = None
+    newest_file = None
+    known_files = set(["NEWS", "ChangeLog", "Changelog", "CHANGES"])
+    for file in known_files:
+        filepath = os.path.join(sourcedir, file)
+        if os.path.isfile(filepath):
+            mtime = int(os.lstat(filepath).st_mtime)
+            # There may be more than one "known_file" present, if so, use the youngest one
+            if not source_date_epoch or mtime > source_date_epoch:
+                source_date_epoch = mtime
+                newest_file = filepath
+    if newest_file:
+        bb.debug(1, "SOURCE_DATE_EPOCH taken from: %s" % newest_file)
+    return source_date_epoch
+
+def find_git_folder(d, sourcedir):
+    # First guess: WORKDIR/git
+    # This is the default git fetcher unpack path
+    workdir = d.getVar('WORKDIR')
+    gitpath = os.path.join(workdir, "git/.git")
+    if os.path.isdir(gitpath):
+        return gitpath
+
+    # Second guess: ${S}
+    gitpath = os.path.join(sourcedir, ".git")
+    if os.path.isdir(gitpath):
+        return gitpath
+
+    # Perhaps there was a subpath or destsuffix specified.
+    # Go looking in the WORKDIR
+    exclude = set(["build", "image", "license-destdir", "patches", "pseudo",
+                   "recipe-sysroot", "recipe-sysroot-native", "sysroot-destdir", "temp"])
+    for root, dirs, files in os.walk(workdir, topdown=True):
+        dirs[:] = [d for d in dirs if d not in exclude]
+        if '.git' in dirs:
+            return root
+
+    bb.warn("Failed to find a git repository in WORKDIR: %s" % workdir)
+    return None
+
+def get_source_date_epoch_from_git(d, sourcedir):
+    source_date_epoch = None
+    if "git://" in d.getVar('SRC_URI'):
+        gitpath = find_git_folder(d, sourcedir)
+        if gitpath:
+            import subprocess
+            source_date_epoch = int(subprocess.check_output(['git','log','-1','--pretty=%ct'], cwd=gitpath))
+            bb.debug(1, "git repository: %s" % gitpath)
+    return source_date_epoch
+
+def get_source_date_epoch_from_youngest_file(d, sourcedir):
+    if sourcedir == d.getVar('WORKDIR'):
+       # These sources are almost certainly not from a tarball
+       return None
+
+    # Do it the hard way: check all files and find the youngest one...
+    source_date_epoch = None
+    newest_file = None
+    for root, dirs, files in os.walk(sourcedir, topdown=True):
+        files = [f for f in files if not f[0] == '.']
+
+        for fname in files:
+            filename = os.path.join(root, fname)
+            try:
+                mtime = int(os.lstat(filename).st_mtime)
+            except ValueError:
+                mtime = 0
+            if not source_date_epoch or mtime > source_date_epoch:
+                source_date_epoch = mtime
+                newest_file = filename
+
+    if newest_file:
+        bb.debug(1, "Newest file found: %s" % newest_file)
+    return source_date_epoch
+
+def fixed_source_date_epoch():
+    bb.debug(1, "No tarball or git repo found to determine SOURCE_DATE_EPOCH")
+    return 0
+
+def get_source_date_epoch(d, sourcedir):
+    return (
+        get_source_date_epoch_from_git(d, sourcedir) or
+        get_source_date_epoch_from_known_files(d, sourcedir) or
+        get_source_date_epoch_from_youngest_file(d, sourcedir) or
+        fixed_source_date_epoch()       # Last resort
+    )
+