view tests/test-eol.out @ 12252:4481f8a93c7a stable

convert/darcs: handle non-ASCII metadata in darcs changelog (issue2354)

Given a commit author or message with non-ASCII characters in a darcs
repo, convert would raise a UnicodeEncodeError when adding changesets
to the hg changelog.

This happened because etree returns back unicode objects for any text
it can't encode into ASCII. convert was passing these objects to
changelog.add(), which would then attempt encoding.fromlocal() on
them.

This patch ensures converter_source.recode() is called on each piece
of commit data returned by etree.

(Also note that darcs is currently encoding agnostic and will print
out whatever is in a patch's metadata byte-for-byte, even in the XML
changelog.)

% setup LF repository
adding .hgeol
adding a.txt

% hg clone repo repo-LF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% printrepr.py a.txt
first
second
third
% hg cat a.txt
first
second
third
% printrepr.py a.txt
first
second
third
fourth
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first
 second
 third
+fourth
% switching encoding from '\n' to '\r\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first
 second
 third
+fourth
% reverting back to LF format
first
second
third
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt

% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)
% hg clone repo repo-CRLF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% printrepr.py a.txt
first\r
second\r
third\r
% hg cat a.txt
first
second
third
% printrepr.py a.txt
first\r
second\r
third\r
fourth\r
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first
 second
 third
+fourth
% switching encoding from '\r\n' to '\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first
 second
 third
+fourth
% reverting back to CRLF format
first\r
second\r
third\r
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt

% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)
% setup CRLF repository
adding .hgeol
adding a.txt

% hg clone repo repo-LF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% printrepr.py a.txt
first
second
third
% hg cat a.txt
first\r
second\r
third\r
% printrepr.py a.txt
first
second
third
fourth
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first\r
 second\r
 third\r
+fourth\r
% switching encoding from '\n' to '\r\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first\r
 second\r
 third\r
+fourth\r
% reverting back to LF format
first
second
third
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt

% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)
% hg clone repo repo-CRLF
2 files updated, 0 files merged, 0 files removed, 0 files unresolved
% printrepr.py a.txt
first\r
second\r
third\r
% hg cat a.txt
first\r
second\r
third\r
% printrepr.py a.txt
first\r
second\r
third\r
fourth\r
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first\r
 second\r
 third\r
+fourth\r
% switching encoding from '\r\n' to '\n'
% hg diff only reports a single changed line:
diff --git a/a.txt b/a.txt
--- a/a.txt
+++ b/a.txt
@@ -1,3 +1,4 @@
 first\r
 second\r
 third\r
+fourth\r
% reverting back to CRLF format
first\r
second\r
third\r
% hg commit of inconsistent .txt file marked as binary (should work)
% hg commit of inconsistent .txt file marked as native (should fail)
abort: inconsistent newline style in a.txt

% hg commit --config eol.only-consistent=False (should work)
% hg commit of binary .txt file marked as native (binary files always okay)

# setup LF repository
adding unix.txt
adding win.txt
# setting repository-native EOLs to LF
adding .hgeol

% hg clone mixed mixed-LF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M win.txt
% hg commit
% hg status

% hg clone mixed mixed-CRLF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M win.txt
% hg commit
% hg status

# setup CRLF repository
adding unix.txt
adding win.txt
# setting repository-native EOLs to CRLF
adding .hgeol

% hg clone mixed mixed-LF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M unix.txt
% hg commit
% hg status

% hg clone mixed mixed-CRLF
updating to branch default
3 files updated, 0 files merged, 0 files removed, 0 files unresolved
% hg status (eol extension not yet activated)
% hg status (eol activated)
M unix.txt
% hg commit
% hg status