fetch2: Add API for upstream source tracingalpianon/srctrace6

This patch adds an API to bb.fetch2 to enable users to plug in an unpack
tracer that can trace each source file back to its corresponding
upstream source url, even when multiple upstream sources are combined
together in the same unpack directory. This may be required for software
composition analysis, license compliance, and detailed SBoM generation.

This patch provides only the needed hooks in bb.fetch2 code and a dummy
abstract class defining the API; users may load their own unpack tracer
class by setting the BB_UNPACK_TRACER_CLASS config parameter.

Signed-off-by: Alberto Pianon <alberto@pianon.eu>

7 files changed, 91 insertions, 0 deletions

diff --git a/lib/bb/fetch2/__init__.py b/lib/bb/fetch2/__init__.py
index ffb1a92b2..35e9ca96b 100644
--- a/lib/bb/fetch2/__init__.py
+++ b/lib/bb/fetch2/__init__.py
@@ -1579,6 +1579,7 @@ class FetchMethod(object):
             unpackdir = rootdir
 
         if not unpack or not cmd:
+            urldata.unpack_tracer.unpack("file-copy", unpackdir)
             # If file == dest, then avoid any copies, as we already put the file into dest!
             dest = os.path.join(unpackdir, os.path.basename(file))
             if file != dest and not (os.path.exists(dest) and os.path.samefile(file, dest)):
@@ -1593,6 +1594,8 @@ class FetchMethod(object):
                         destdir = urlpath.rsplit("/", 1)[0] + '/'
                         bb.utils.mkdirhier("%s/%s" % (unpackdir, destdir))
                 cmd = 'cp -fpPRH "%s" "%s"' % (file, destdir)
+        else:
+            urldata.unpack_tracer.unpack("archive-extract", unpackdir)
 
         if not cmd:
             return
@@ -1684,6 +1687,55 @@ class FetchMethod(object):
         """
         return []
 
+
+class DummyUnpackTracer(object):
+    """
+    Abstract API definition for a class that traces unpacked source files back
+    to their respective upstream SRC_URI entries, for software composition
+    analysis, license compliance and detailed SBOM generation purposes.
+    User may load their own unpack tracer class (instead of the dummy
+    one) by setting the BB_UNPACK_TRACER_CLASS config parameter.
+    """
+    def start(self, unpackdir, urldata_dict, d):
+        """
+        Start tracing the core Fetch.unpack process, using an index to map
+        unpacked files to each SRC_URI entry.
+        This method is called by Fetch.unpack and it may receive nested calls by
+        gitsm and npmsw fetchers, that expand SRC_URI entries by adding implicit
+        URLs and by recursively calling Fetch.unpack from new (nested) Fetch
+        instances.
+        """
+        return
+    def start_url(self, url):
+        """Start tracing url unpack process.
+        This method is called by Fetch.unpack before the fetcher-specific unpack
+        method starts, and it may receive nested calls by gitsm and npmsw
+        fetchers.
+        """
+        return
+    def unpack(self, unpack_type, destdir):
+        """
+        Set unpack_type and destdir for current url.
+        This method is called by the fetcher-specific unpack method after url
+        tracing started.
+        """
+        return
+    def finish_url(self, url):
+        """Finish tracing url unpack process and update the file index.
+        This method is called by Fetch.unpack after the fetcher-specific unpack
+        method finished its job, and it may receive nested calls by gitsm
+        and npmsw fetchers.
+        """
+        return
+    def complete(self):
+        """
+        Finish tracing the Fetch.unpack process, and check if all nested
+        Fecth.unpack calls (if any) have been completed; if so, save collected
+        metadata.
+        """
+        return
+
+
 class Fetch(object):
     def __init__(self, urls, d, cache = True, localonly = False, connection_cache = None):
         if localonly and cache:
@@ -1704,10 +1756,30 @@ class Fetch(object):
         if key in urldata_cache:
             self.ud = urldata_cache[key]
 
+        # the unpack_tracer object needs to be made available to possible nested
+        # Fetch instances (when those are created by gitsm and npmsw fetchers)
+        # so we set it as a global variable
+        global unpack_tracer
+        try:
+            unpack_tracer
+        except NameError:
+            class_path = d.getVar("BB_UNPACK_TRACER_CLASS")
+            if class_path:
+                # use user-defined unpack tracer class
+                import importlib
+                module_name, _, class_name = class_path.rpartition(".")
+                module = importlib.import_module(module_name)
+                class_ = getattr(module, class_name)
+                unpack_tracer = class_()
+            else:
+                # fall back to the dummy/abstract class
+                unpack_tracer = DummyUnpackTracer()
+
         for url in urls:
             if url not in self.ud:
                 try:
                     self.ud[url] = FetchData(url, d, localonly)
+                    self.ud[url].unpack_tracer = unpack_tracer
                 except NonLocalMethod:
                     if localonly:
                         self.ud[url] = None
@@ -1883,6 +1955,8 @@ class Fetch(object):
         if not urls:
             urls = self.urls
 
+        unpack_tracer.start(root, self.ud, self.d)
+
         for u in urls:
             ud = self.ud[u]
             ud.setup_localpath(self.d)
@@ -1890,11 +1964,15 @@ class Fetch(object):
             if ud.lockfile:
                 lf = bb.utils.lockfile(ud.lockfile)
 
+            unpack_tracer.start_url(u)
             ud.method.unpack(ud, root, self.d)
+            unpack_tracer.finish_url(u)
 
             if ud.lockfile:
                 bb.utils.unlockfile(lf)
 
+        unpack_tracer.complete()
+
     def clean(self, urls=None):
         """
         Clean files that the fetcher gets or places
diff --git a/lib/bb/fetch2/crate.py b/lib/bb/fetch2/crate.py
index 3310ed005..01d49435c 100644
--- a/lib/bb/fetch2/crate.py
+++ b/lib/bb/fetch2/crate.py
@@ -101,8 +101,10 @@ class Crate(Wget):
         bp = d.getVar('BP')
         if bp == ud.parm.get('name'):
             cmd = "tar -xz --no-same-owner -f %s" % thefile
+            ud.unpack_tracer.unpack("crate-extract", rootdir)
         else:
             cargo_bitbake = self._cargo_bitbake_path(rootdir)
+            ud.unpack_tracer.unpack("cargo-extract", cargo_bitbake)
 
             cmd = "tar -xz --no-same-owner -f %s -C %s" % (thefile, cargo_bitbake)
 
diff --git a/lib/bb/fetch2/git.py b/lib/bb/fetch2/git.py
index 4385d0b37..c7ed1f036 100644
--- a/lib/bb/fetch2/git.py
+++ b/lib/bb/fetch2/git.py
@@ -589,6 +589,8 @@ class Git(FetchMethod):
         destdir = ud.destdir = os.path.join(destdir, destsuffix)
         if os.path.exists(destdir):
             bb.utils.prunedir(destdir)
+        if not ud.bareclone:
+            ud.unpack_tracer.unpack("git", destdir)
 
         need_lfs = self._need_lfs(ud)
 
diff --git a/lib/bb/fetch2/gitsm.py b/lib/bb/fetch2/gitsm.py
index a87361ccf..f7f3af721 100644
--- a/lib/bb/fetch2/gitsm.py
+++ b/lib/bb/fetch2/gitsm.py
@@ -218,6 +218,10 @@ class GitSM(Git):
 
             try:
                 newfetch = Fetch([url], d, cache=False)
+                # modpath is needed by unpack tracer to calculate submodule
+                # checkout dir
+                new_ud = newfetch.ud[url]
+                new_ud.modpath = modpath
                 newfetch.unpack(root=os.path.dirname(os.path.join(repo_conf, 'modules', module)))
             except Exception as e:
                 logger.error('gitsm: submodule unpack failed: %s %s' % (type(e).__name__, str(e)))
diff --git a/lib/bb/fetch2/hg.py b/lib/bb/fetch2/hg.py
index 063e13008..cbff8c490 100644
--- a/lib/bb/fetch2/hg.py
+++ b/lib/bb/fetch2/hg.py
@@ -242,6 +242,7 @@ class Hg(FetchMethod):
         revflag = "-r %s" % ud.revision
         subdir = ud.parm.get("destsuffix", ud.module)
         codir = "%s/%s" % (destdir, subdir)
+        ud.unpack_tracer.unpack("hg", codir)
 
         scmdata = ud.parm.get("scmdata", "")
         if scmdata != "nokeep":
diff --git a/lib/bb/fetch2/npm.py b/lib/bb/fetch2/npm.py
index f83485ad8..15f3f19bc 100644
--- a/lib/bb/fetch2/npm.py
+++ b/lib/bb/fetch2/npm.py
@@ -298,6 +298,7 @@ class Npm(FetchMethod):
         destsuffix = ud.parm.get("destsuffix", "npm")
         destdir = os.path.join(rootdir, destsuffix)
         npm_unpack(ud.localpath, destdir, d)
+        ud.unpack_tracer.unpack("npm", destdir)
 
     def clean(self, ud, d):
         """Clean any existing full or partial download"""
diff --git a/lib/bb/fetch2/npmsw.py b/lib/bb/fetch2/npmsw.py
index 4ff2c8ffc..ff5f8dc75 100644
--- a/lib/bb/fetch2/npmsw.py
+++ b/lib/bb/fetch2/npmsw.py
@@ -191,7 +191,9 @@ class NpmShrinkWrap(FetchMethod):
             else:
                 raise ParameterError("Unsupported dependency: %s" % name, ud.url)
 
+            # name is needed by unpack tracer for module mapping
             ud.deps.append({
+                "name": name,
                 "url": url,
                 "localpath": localpath,
                 "extrapaths": extrapaths,
@@ -270,6 +272,7 @@ class NpmShrinkWrap(FetchMethod):
         destsuffix = ud.parm.get("destsuffix")
         if destsuffix:
             destdir = os.path.join(rootdir, destsuffix)
+        ud.unpack_tracer.unpack("npm-shrinkwrap", destdir)
 
         bb.utils.mkdirhier(destdir)
         bb.utils.copyfile(ud.shrinkwrap_file,