project: Use dicts to keep track of copyfiles and linkfiles

This avoids copying/linking the same file/link multiple times if a
copyfile/linkfile element with the same values has been specifed
multiple times. This can happen when including a common manifest that
uses an extend-project element that has a copyfile/linkfile element.

This uses dicts rather than sets to store the copyfiles and linkfiles to
make sure the order they are specified in the manifest is maintained.
For Python 3.7+, maintaining the order that keys are added to dicts is
guaranteed, and for Python 3.6 it happened to be true.

The _CopyFile class and the _LinkFile class are changed to inherit from
NamedTuple to be able to store them in dicts.

Change-Id: I9f5a80298b875251a81c5fe7d353e262d104fae4
Reviewed-on: https://gerrit-review.googlesource.com/c/git-repo/+/525322
Reviewed-by: Mike Frysinger <vapier@google.com>
Reviewed-by: Gavin Mak <gavinmak@google.com>
Tested-by: Peter Kjellerstedt <peter.kjellerstedt@axis.com>
Commit-Queue: Peter Kjellerstedt <peter.kjellerstedt@axis.com>

1 files changed, 23 insertions, 32 deletions

diff --git a/project.py b/project.py
index 8e430175..41606442 100644
--- a/project.py
+++ b/project.py
@@ -390,22 +390,17 @@ def _SafeExpandPath(base, subpath, skipfinal=False):
     return path
 
 
-class _CopyFile:
+class _CopyFile(NamedTuple):
     """Container for <copyfile> manifest element."""
 
-    def __init__(self, git_worktree, src, topdir, dest):
-        """Register a <copyfile> request.
-
-        Args:
-            git_worktree: Absolute path to the git project checkout.
-            src: Relative path under |git_worktree| of file to read.
-            topdir: Absolute path to the top of the repo client checkout.
-            dest: Relative path under |topdir| of file to write.
-        """
-        self.git_worktree = git_worktree
-        self.topdir = topdir
-        self.src = src
-        self.dest = dest
+    # Absolute path to the git project checkout.
+    git_worktree: str
+    # Relative path under |git_worktree| of file to read.
+    src: str
+    # Absolute path to the top of the repo client checkout.
+    topdir: str
+    # Relative path under |topdir| of file to write.
+    dest: str
 
     def _Copy(self):
         src = _SafeExpandPath(self.git_worktree, self.src)
@@ -439,22 +434,17 @@ class _CopyFile:
                 logger.error("error: Cannot copy file %s to %s", src, dest)
 
 
-class _LinkFile:
+class _LinkFile(NamedTuple):
     """Container for <linkfile> manifest element."""
 
-    def __init__(self, git_worktree, src, topdir, dest):
-        """Register a <linkfile> request.
-
-        Args:
-            git_worktree: Absolute path to the git project checkout.
-            src: Target of symlink relative to path under |git_worktree|.
-            topdir: Absolute path to the top of the repo client checkout.
-            dest: Relative path under |topdir| of symlink to create.
-        """
-        self.git_worktree = git_worktree
-        self.topdir = topdir
-        self.src = src
-        self.dest = dest
+    # Absolute path to the git project checkout.
+    git_worktree: str
+    # Target of symlink relative to path under |git_worktree|.
+    src: str
+    # Absolute path to the top of the repo client checkout.
+    topdir: str
+    # Relative path under |topdir| of symlink to create.
+    dest: str
 
     def __linkIt(self, relSrc, absDest):
         # Link file if it does not exist or is out of date.
@@ -633,8 +623,9 @@ class Project:
         self.subprojects = []
 
         self.snapshots = {}
-        self.copyfiles = []
-        self.linkfiles = []
+        # Use dicts to dedupe while maintaining declared order.
+        self.copyfiles = {}
+        self.linkfiles = {}
         self.annotations = []
         self.dest_branch = dest_branch
 
@@ -1794,7 +1785,7 @@ class Project:
         Paths should have basic validation run on them before being queued.
         Further checking will be handled when the actual copy happens.
         """
-        self.copyfiles.append(_CopyFile(self.worktree, src, topdir, dest))
+        self.copyfiles[_CopyFile(self.worktree, src, topdir, dest)] = True
 
     def AddLinkFile(self, src, dest, topdir):
         """Mark |dest| to create a symlink (relative to |topdir|) pointing to
@@ -1805,7 +1796,7 @@ class Project:
         Paths should have basic validation run on them before being queued.
         Further checking will be handled when the actual link happens.
         """
-        self.linkfiles.append(_LinkFile(self.worktree, src, topdir, dest))
+        self.linkfiles[_LinkFile(self.worktree, src, topdir, dest)] = True
 
     def AddAnnotation(self, name, value, keep):
         self.annotations.append(Annotation(name, value, keep))