From ac0e2bbcc99b07ea5185041f5a066c36cc1e42ac Mon Sep 17 00:00:00 2001
From: Jim Porter <jporterbugs@gmail.com>
Date: Wed, 12 Apr 2023 23:03:31 -0700
Subject: [PATCH] [WIP] Add Git hooks to check filenames listed in the commit
 message

* build-aux/git-hooks/commit-msg-files.awk:
* build-aux/git-hooks/post-commit:
* build-aux/git-hooks/pre-push: New files.
---
 build-aux/git-hooks/commit-msg-files.awk | 39 +++++++++++++++++++
 build-aux/git-hooks/post-commit          | 19 +++++++++
 build-aux/git-hooks/pre-push             | 49 ++++++++++++++++++++++++
 3 files changed, 107 insertions(+)
 create mode 100644 build-aux/git-hooks/commit-msg-files.awk
 create mode 100644 build-aux/git-hooks/post-commit
 create mode 100644 build-aux/git-hooks/pre-push

diff --git a/build-aux/git-hooks/commit-msg-files.awk b/build-aux/git-hooks/commit-msg-files.awk
new file mode 100644
index 00000000000..1dd89dcdea0
--- /dev/null
+++ b/build-aux/git-hooks/commit-msg-files.awk
@@ -0,0 +1,39 @@
+function get_commit_changes(commit_sha, changes,    i, j, len, bits, filename) {
+  # Collect all the files touched in the specified commit.
+  while ((("git log -1 --name-status --format= " commit_sha) | getline) > 0) {
+    for (i = 2; i <= NF; i++) {
+      len = split($i, bits, "/")
+      for (j = 1; j <= len; j++) {
+        if (j == 1)
+          filename = bits[j]
+        else
+          filename = filename "/" bits[j]
+        changes[filename] = 1
+      }
+    }
+  }
+}
+
+function check_commit_msg_files(commit_sha,    changes, good, msg, filename) {
+  get_commit_changes(commit_sha, changes)
+  good = 1
+
+  while ((("git log -1 --format=%B " commit_sha) | getline) > 0) {
+    if (! msg)
+      msg = $0
+
+    if (/^\* / && match($2, "[^:/][^:]*")) {
+      filename = substr($2, RSTART, RLENGTH)
+      if (! (filename in changes)) {
+        if (good) {
+          printf("In commit %s: %s\n", substr(commit_sha, 1, 10), msg)
+        }
+        printf("  File %s listed in commit message, but not in diff\n",
+               filename)
+        good = 0
+      }
+    }
+  }
+
+  return good
+}
diff --git a/build-aux/git-hooks/post-commit b/build-aux/git-hooks/post-commit
new file mode 100644
index 00000000000..35c902d8270
--- /dev/null
+++ b/build-aux/git-hooks/post-commit
@@ -0,0 +1,19 @@
+#!/bin/sh
+
+git rev-parse HEAD | awk '
+  # FIXME: Do this a POSIX-compatible way.
+  @include ".git/hooks/commit-msg-files.awk"
+
+  /^[a-z0-9]{40}$/ {
+    if (! check_commit_msg_files($0)) {
+      status = 1
+    }
+  }
+
+  END {
+    if (status != 0) {
+      print "Bad commit message; please see the file '\''CONTRIBUTE'\''"
+    }
+    exit status
+  }
+'
diff --git a/build-aux/git-hooks/pre-push b/build-aux/git-hooks/pre-push
new file mode 100644
index 00000000000..3329bf59e1d
--- /dev/null
+++ b/build-aux/git-hooks/pre-push
@@ -0,0 +1,49 @@
+#!/bin/sh
+
+awk -v origin_name="$1" '
+  @include ".git/hooks/commit-msg-files.awk"
+
+  # If the local SHA is all zeroes, ignore it.
+  $2 ~ /^0{40}$/ {
+    next
+  }
+
+  $2 ~ /^[a-z0-9]{40}$/ {
+    newref = $2
+
+    # If the remote SHA is all zeroes, go backwards until we find a SHA on
+    # an origin branch.
+    if ($4 ~ /^0{40}$/) {
+      back = 0
+      while ((("git branch -r -l '\''" origin_name "/*'\'' --contains " \
+               newref "~" back) | getline) == 0) {
+        back++
+      }
+
+      ("git rev-parse " newref "~" back) | getline oldref
+      if (!(oldref ~ /^[a-z0-9]{40}$/)) {
+        # The SHA is misformatted?!
+        exit 2
+      }
+    } else if ($4 ~ /^[a-z0-9]{40}$/)  {
+      oldref = $4
+    } else {
+      # The remote SHA is misformatted?!
+      exit 2
+    }
+
+    # Iterate over every SHA after oldref, up to (and including) newref.
+    while ((("git rev-list --reverse " oldref ".." newref) | getline) > 0) {
+      if (! check_commit_msg_files($0)) {
+        status = 1
+      }
+    }
+  }
+
+  END {
+    if (status != 0) {
+      print "Push aborted; please see the file '\''CONTRIBUTE'\''"
+    }
+    exit status
+  }
+'
-- 
2.25.1