[JGIT PATCH] The default encoding for reading commits is UTF-8 rather than system default
From: Constantine Plotnikov <hidden>
Date: 2016-06-15 22:47:29
When reading commits the system default encoding was used if no encoding was specified in the commit. The patch modifies test to add a check that commit message was encoded correctly (the test fails on old implementation if system encoding is not UTF-8) and fixes Commit.decode() method to use UTF-8 is encoding is not specified in the commit object. Signed-off-by: Constantine Plotnikov <redacted> --- See man git-commit (the section "DISCUSSION"), for justification why UTF-8 should be used. Note that this was already correctly implemented in ObjectWriter.writeCommit(...) method. But Commit.decode() was not implemented in the same way for some reason. .../tst/org/spearce/jgit/lib/T0003_Basic.java | 3 +++ .../src/org/spearce/jgit/lib/Commit.java | 18 +++++++----------- 2 files changed, 10 insertions(+), 11 deletions(-)
diff --git a/org.spearce.jgit.test/tst/org/spearce/jgit/lib/T0003_Basic.java b/org.spearce.jgit.test/tst/org/spearce/jgit/lib/T0003_Basic.java
index c2b1b91..4702aaf 100644
--- a/org.spearce.jgit.test/tst/org/spearce/jgit/lib/T0003_Basic.java
+++ b/org.spearce.jgit.test/tst/org/spearce/jgit/lib/T0003_Basic.java@@ -348,6 +348,9 @@ public void test023_createCommitNonAnullii() throws IOException { commit.setMessage("\u00dcbergeeks"); ObjectId cid = new ObjectWriter(db).writeCommit(commit); assertEquals("4680908112778718f37e686cbebcc912730b3154", cid.name()); + Commit loadedCommit = db.mapCommit(cid); + assertNotSame(loadedCommit, commit); + assertEquals(commit.getMessage(), loadedCommit.getMessage()); } public void test024_createCommitNonAscii() throws IOException {
diff --git a/org.spearce.jgit/src/org/spearce/jgit/lib/Commit.java b/org.spearce.jgit/src/org/spearce/jgit/lib/Commit.java
index 030d4a4..933b929 100644
--- a/org.spearce.jgit/src/org/spearce/jgit/lib/Commit.java
+++ b/org.spearce.jgit/src/org/spearce/jgit/lib/Commit.java@@ -299,17 +299,13 @@ private void decode() { br.read(readBuf); int msgstart = readBuf.length != 0 ? ( readBuf[0] == '\n' ? 1 : 0 ) : 0; - if (encoding != null) { - // TODO: this isn't reliable so we need to guess the encoding from the actual content - author = new PersonIdent(new String(rawAuthor.getBytes(),encoding.name())); - committer = new PersonIdent(new String(rawCommitter.getBytes(),encoding.name())); - message = new String(readBuf,msgstart, readBuf.length-msgstart, encoding.name()); - } else { - // TODO: use config setting / platform / ascii / iso-latin - author = new PersonIdent(new String(rawAuthor.getBytes())); - committer = new PersonIdent(new String(rawCommitter.getBytes())); - message = new String(readBuf, msgstart, readBuf.length-msgstart); - } + // If encoding is not specified, the default for commit is UTF-8 + if (encoding == null) encoding = Constants.CHARSET; + + // TODO: this isn't reliable so we need to guess the encoding from the actual content + author = new PersonIdent(new String(rawAuthor.getBytes(),encoding.name())); + committer = new PersonIdent(new String(rawCommitter.getBytes(),encoding.name())); + message = new String(readBuf,msgstart, readBuf.length-msgstart, encoding.name()); } catch (IOException e) { e.printStackTrace(); } finally {
--
1.6.1.2