bitbake: fetch2: Add gomodgit fetcher

Add a go module fetcher for downloading module dependencies to the
module cache directly from a git repository. The fetcher can be used
with the go-mod class in OE-Core.

A module dependency can be specified with:

  SRC_URI += "gomodgit://golang.org/x/net;version=v0.9.0;srcrev=..."

(Bitbake rev: 29ff38ccf0d5389a5bee81e252a78548361a9d7c)

Signed-off-by: Christian Lindeberg <christian.lindeberg@axis.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

3 files changed, 228 insertions, 2 deletions

diff --git a/bitbake/lib/bb/fetch2/__init__.py b/bitbake/lib/bb/fetch2/__init__.py
index f84ce59992..ddee4400bb 100644
--- a/bitbake/lib/bb/fetch2/__init__.py
+++ b/bitbake/lib/bb/fetch2/__init__.py
@@ -2112,3 +2112,4 @@ methods.append(az.Az())
 methods.append(crate.Crate())
 methods.append(gcp.GCP())
 methods.append(gomod.GoMod())
+methods.append(gomod.GoModGit())
diff --git a/bitbake/lib/bb/fetch2/gomod.py b/bitbake/lib/bb/fetch2/gomod.py
index fe025e367f..1b532d03ff 100644
--- a/bitbake/lib/bb/fetch2/gomod.py
+++ b/bitbake/lib/bb/fetch2/gomod.py
@@ -1,12 +1,13 @@
 """
 BitBake 'Fetch' implementation for Go modules
 
-The gomod fetcher is used to download Go modules to the module cache from a
-module proxy.
+The gomod/gomodgit fetchers are used to download Go modules to the module cache
+from a module proxy or directly from a version control repository.
 
 Example SRC_URI:
 
 SRC_URI += "gomod://golang.org/x/net;version=v0.9.0;sha256sum=..."
+SRC_URI += "gomodgit://golang.org/x/net;version=v0.9.0;repo=go.googlesource.com/net;srcrev=..."
 
 Required SRC_URI parameters:
 
@@ -27,6 +28,23 @@ Optional SRC_URI parameters:
     only the go.mod file. Alternatively, set the SRC_URI varible flag for
     "module@version.sha256sum".
 
+- protocol
+    The method used when fetching directly from a version control repository.
+    The default is "https" for git.
+
+- repo
+    The URL when fetching directly from a version control repository. Required
+    when the URL is different from the module path.
+
+- srcrev
+    The revision identifier used when fetching directly from a version control
+    repository. Alternatively, set the SRCREV varible for "module@version".
+
+- subdir
+    The module subdirectory when fetching directly from a version control
+    repository. Required when the module is not located in the root of the
+    repository.
+
 Related variables:
 
 - GO_MOD_PROXY
@@ -41,14 +59,19 @@ See the Go modules reference, https://go.dev/ref/mod, for more information
 about the module cache, module proxies and version control systems.
 """
 
+import hashlib
 import os
 import re
 import shutil
+import subprocess
 import zipfile
 
 import bb
 from bb.fetch2 import FetchError
 from bb.fetch2 import MissingParameterError
+from bb.fetch2 import runfetchcmd
+from bb.fetch2 import subprocess_setup
+from bb.fetch2.git import Git
 from bb.fetch2.wget import Wget
 
 
@@ -126,3 +149,116 @@ class GoMod(Wget):
                         # If the module does not have a go.mod file, synthesize
                         # one containing only a module statement.
                         mf.write(f'module {module}\n'.encode())
+
+
+class GoModGit(Git):
+    """Class to fetch Go modules directly from a git repository"""
+
+    def supports(self, ud, d):
+        """Check to see if a given URL is for this fetcher."""
+        return ud.type == 'gomodgit'
+
+    def urldata_init(self, ud, d):
+        """Set up to download the module from the git repository.
+
+        Set up to download the git repository to the module cache directory and
+        unpack the module zip file and the go.mod file:
+
+        cache/vcs/<hash>:                         The bare git repository.
+        cache/download/<module>/@v/<version>.zip: The module zip file.
+        cache/download/<module>/@v/<version>.mod: The go.mod file.
+        """
+
+        moddir = d.getVar('GO_MOD_CACHE_DIR') or 'pkg/mod'
+
+        if 'version' not in ud.parm:
+            raise MissingParameterError('version', ud.url)
+
+        module = ud.host + ud.path
+        ud.parm['module'] = module
+
+        # Set host, path and srcrev for git download
+        if 'repo' in ud.parm:
+            repo = ud.parm['repo']
+            idx = repo.find('/')
+            if idx != -1:
+                ud.host = repo[:idx]
+                ud.path = repo[idx:]
+            else:
+                ud.host = repo
+                ud.path = ''
+        if 'protocol' not in ud.parm:
+            ud.parm['protocol'] = 'https'
+        name = f"{module}@{ud.parm['version']}"
+        ud.names = [name]
+        srcrev = d.getVar('SRCREV_' + name)
+        if srcrev:
+            if 'srcrev' not in ud.parm:
+                ud.parm['srcrev'] = srcrev
+        else:
+            if 'srcrev' in ud.parm:
+                d.setVar('SRCREV_' + name, ud.parm['srcrev'])
+        if 'branch' not in ud.parm:
+            ud.parm['nobranch'] = '1'
+
+        # Set subpath, subdir and bareclone for git unpack
+        if 'subdir' in ud.parm:
+            ud.parm['subpath'] = ud.parm['subdir']
+        key = f"git3:{ud.parm['protocol']}://{ud.host}{ud.path}".encode()
+        ud.parm['key'] = key
+        ud.parm['subdir'] = os.path.join(moddir, 'cache/vcs',
+                                         hashlib.sha256(key).hexdigest())
+        ud.parm['bareclone'] = '1'
+
+        super().urldata_init(ud, d)
+
+    def unpack(self, ud, rootdir, d):
+        """Unpack the module in the module cache."""
+
+        # Unpack the bare git repository
+        super().unpack(ud, rootdir, d)
+
+        moddir = d.getVar('GO_MOD_CACHE_DIR') or 'pkg/mod'
+
+        # Create the info file
+        module = ud.parm['module']
+        repodir = os.path.join(rootdir, ud.parm['subdir'])
+        with open(repodir + '.info', 'wb') as f:
+            f.write(ud.parm['key'])
+
+        # Unpack the go.mod file from the repository
+        unpackdir = os.path.join(rootdir, moddir, 'cache/download',
+                                 escape(module), '@v')
+        bb.utils.mkdirhier(unpackdir)
+        srcrev = ud.parm['srcrev']
+        version = ud.parm['version']
+        escaped_version = escape(version)
+        cmd = f"git ls-tree -r --name-only '{srcrev}'"
+        if 'subpath' in ud.parm:
+            cmd += f" '{ud.parm['subpath']}'"
+        files = runfetchcmd(cmd, d, workdir=repodir).split()
+        name = escaped_version + '.mod'
+        bb.note(f"Unpacking {name} to {unpackdir}/")
+        with open(os.path.join(unpackdir, name), mode='wb') as mf:
+            f = 'go.mod'
+            if 'subpath' in ud.parm:
+                f = os.path.join(ud.parm['subpath'], f)
+            if f in files:
+                cmd = ['git', 'cat-file', 'blob', srcrev + ':' + f]
+                subprocess.check_call(cmd, stdout=mf, cwd=repodir,
+                                      preexec_fn=subprocess_setup)
+            else:
+                # If the module does not have a go.mod file, synthesize one
+                # containing only a module statement.
+                mf.write(f'module {module}\n'.encode())
+
+        # Synthesize the module zip file from the repository
+        name = escaped_version + '.zip'
+        bb.note(f"Unpacking {name} to {unpackdir}/")
+        with zipfile.ZipFile(os.path.join(unpackdir, name), mode='w') as zf:
+            prefix = module + '@' + version + '/'
+            for f in files:
+                cmd = ['git', 'cat-file', 'blob', srcrev + ':' + f]
+                data = subprocess.check_output(cmd, cwd=repodir,
+                                               preexec_fn=subprocess_setup)
+                zf.writestr(prefix + f, data)
diff --git a/bitbake/lib/bb/tests/fetch.py b/bitbake/lib/bb/tests/fetch.py
index 2365a50960..832e0dd6a4 100644
--- a/bitbake/lib/bb/tests/fetch.py
+++ b/bitbake/lib/bb/tests/fetch.py
@@ -3455,3 +3455,92 @@ class GoModTest(FetcherTest):
         downloaddir = os.path.join(self.unpackdir, 'pkg/mod/cache/download')
         self.assertTrue(os.path.exists(os.path.join(downloaddir, 'gopkg.in/ini.v1/@v/v1.67.0.zip')))
         self.assertTrue(os.path.exists(os.path.join(downloaddir, 'gopkg.in/ini.v1/@v/v1.67.0.mod')))
+
+class GoModGitTest(FetcherTest):
+
+    @skipIfNoNetwork()
+    def test_gomodgit_url_repo(self):
+        urls = ['gomodgit://golang.org/x/net;version=v0.9.0;'
+                'repo=go.googlesource.com/net;'
+                'srcrev=694cff8668bac64e0864b552bffc280cd27f21b1']
+
+        fetcher = bb.fetch2.Fetch(urls, self.d)
+        ud = fetcher.ud[urls[0]]
+        self.assertEqual(ud.host, 'go.googlesource.com')
+        self.assertEqual(ud.path, '/net')
+        self.assertEqual(ud.names, ['golang.org/x/net@v0.9.0'])
+        self.assertEqual(self.d.getVar('SRCREV_golang.org/x/net@v0.9.0'), '694cff8668bac64e0864b552bffc280cd27f21b1')
+
+        fetcher.download()
+        self.assertTrue(os.path.exists(ud.localpath))
+
+        fetcher.unpack(self.unpackdir)
+        vcsdir = os.path.join(self.unpackdir, 'pkg/mod/cache/vcs')
+        self.assertTrue(os.path.exists(os.path.join(vcsdir, 'ed42bd05533fd84ae290a5d33ebd3695a0a2b06131beebd5450825bee8603aca')))
+        downloaddir = os.path.join(self.unpackdir, 'pkg/mod/cache/download')
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'golang.org/x/net/@v/v0.9.0.zip')))
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'golang.org/x/net/@v/v0.9.0.mod')))
+
+    @skipIfNoNetwork()
+    def test_gomodgit_url_subdir(self):
+        urls = ['gomodgit://github.com/Azure/azure-sdk-for-go/sdk/storage/azblob;version=v1.0.0;'
+                'repo=github.com/Azure/azure-sdk-for-go;subdir=sdk/storage/azblob;'
+                'srcrev=ec928e0ed34db682b3f783d3739d1c538142e0c3']
+
+        fetcher = bb.fetch2.Fetch(urls, self.d)
+        ud = fetcher.ud[urls[0]]
+        self.assertEqual(ud.host, 'github.com')
+        self.assertEqual(ud.path, '/Azure/azure-sdk-for-go')
+        self.assertEqual(ud.parm['subpath'], 'sdk/storage/azblob')
+        self.assertEqual(ud.names, ['github.com/Azure/azure-sdk-for-go/sdk/storage/azblob@v1.0.0'])
+        self.assertEqual(self.d.getVar('SRCREV_github.com/Azure/azure-sdk-for-go/sdk/storage/azblob@v1.0.0'), 'ec928e0ed34db682b3f783d3739d1c538142e0c3')
+
+        fetcher.download()
+        self.assertTrue(os.path.exists(ud.localpath))
+
+        fetcher.unpack(self.unpackdir)
+        vcsdir = os.path.join(self.unpackdir, 'pkg/mod/cache/vcs')
+        self.assertTrue(os.path.exists(os.path.join(vcsdir, 'd31d6145676ed3066ce573a8198f326dea5be45a43b3d8f41ce7787fd71d66b3')))
+        downloaddir = os.path.join(self.unpackdir, 'pkg/mod/cache/download')
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'github.com/!azure/azure-sdk-for-go/sdk/storage/azblob/@v/v1.0.0.zip')))
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'github.com/!azure/azure-sdk-for-go/sdk/storage/azblob/@v/v1.0.0.mod')))
+
+    @skipIfNoNetwork()
+    def test_gomodgit_url_srcrev_var(self):
+        urls = ['gomodgit://gopkg.in/ini.v1;version=v1.67.0']
+        self.d.setVar('SRCREV_gopkg.in/ini.v1@v1.67.0', 'b2f570e5b5b844226bbefe6fb521d891f529a951')
+
+        fetcher = bb.fetch2.Fetch(urls, self.d)
+        ud = fetcher.ud[urls[0]]
+        self.assertEqual(ud.host, 'gopkg.in')
+        self.assertEqual(ud.path, '/ini.v1')
+        self.assertEqual(ud.names, ['gopkg.in/ini.v1@v1.67.0'])
+        self.assertEqual(ud.parm['srcrev'], 'b2f570e5b5b844226bbefe6fb521d891f529a951')
+
+        fetcher.download()
+        fetcher.unpack(self.unpackdir)
+        vcsdir = os.path.join(self.unpackdir, 'pkg/mod/cache/vcs')
+        self.assertTrue(os.path.exists(os.path.join(vcsdir, 'b7879a4be9ba8598851b8278b14c4f71a8316be64913298d1639cce6bde59bc3')))
+        downloaddir = os.path.join(self.unpackdir, 'pkg/mod/cache/download')
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'gopkg.in/ini.v1/@v/v1.67.0.zip')))
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'gopkg.in/ini.v1/@v/v1.67.0.mod')))
+
+    @skipIfNoNetwork()
+    def test_gomodgit_url_no_go_mod_in_module(self):
+        urls = ['gomodgit://gopkg.in/ini.v1;version=v1.67.0;'
+                'srcrev=b2f570e5b5b844226bbefe6fb521d891f529a951']
+
+        fetcher = bb.fetch2.Fetch(urls, self.d)
+        ud = fetcher.ud[urls[0]]
+        self.assertEqual(ud.host, 'gopkg.in')
+        self.assertEqual(ud.path, '/ini.v1')
+        self.assertEqual(ud.names, ['gopkg.in/ini.v1@v1.67.0'])
+        self.assertEqual(self.d.getVar('SRCREV_gopkg.in/ini.v1@v1.67.0'), 'b2f570e5b5b844226bbefe6fb521d891f529a951')
+
+        fetcher.download()
+        fetcher.unpack(self.unpackdir)
+        vcsdir = os.path.join(self.unpackdir, 'pkg/mod/cache/vcs')
+        self.assertTrue(os.path.exists(os.path.join(vcsdir, 'b7879a4be9ba8598851b8278b14c4f71a8316be64913298d1639cce6bde59bc3')))
+        downloaddir = os.path.join(self.unpackdir, 'pkg/mod/cache/download')
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'gopkg.in/ini.v1/@v/v1.67.0.zip')))
+        self.assertTrue(os.path.exists(os.path.join(downloaddir, 'gopkg.in/ini.v1/@v/v1.67.0.mod')))