From aee18d0edd88b9db07c3cfb5c13d9889ffac94c1 Mon Sep 17 00:00:00 2001 From: Alberto Bertogli Date: Sun, 24 May 2020 15:52:11 +0100 Subject: Simplify smstr With the Python 2 to 3 migration and the type checking, we can be fairly confident that smstr are always constructed from strings, not bytes. This allows the code to be simplified, as we no longer need to carry the dual raw/unicode representation. --- git.py | 31 +++++++++---------------------- views/blob.html | 10 +++++----- views/tree.html | 4 ++-- 3 files changed, 16 insertions(+), 29 deletions(-) diff --git a/git.py b/git.py index 846c1a6..6cec1cd 100644 --- a/git.py +++ b/git.py @@ -125,28 +125,15 @@ class SimpleNamespace(object): class smstr: - """A "smart" string, containing many representations for ease of use. - - This is a string class that contains: - .raw -> raw string, authoritative source. - .unicode -> unicode representation, may not be perfect if .raw is not - proper utf8 but should be good enough to show. - .url -> escaped for safe embedding in URLs, can be not quite - readable. - .html -> an HTML-embeddable representation. - """ + """A "smart" string, containing many representations for ease of use.""" - def __init__(self, raw: str): - if not isinstance(raw, (str, bytes)): - raise TypeError( - "The raw string must be instance of 'str', not %s" % type(raw) - ) - self.raw = raw - if isinstance(raw, bytes): - self.unicode: str = raw.decode("utf8", errors="backslashreplace") - else: - self.unicode = raw - self.url = urllib.request.pathname2url(raw) + raw: str # string, probably utf8-encoded, good enough to show. + url: str # escaped for safe embedding in URLs (not human-readable). + html: str # HTML-embeddable representation. + + def __init__(self, s: str): + self.raw = s + self.url = urllib.request.pathname2url(s) self.html = self._to_html() def __cmp__(self, other): @@ -173,7 +160,7 @@ class smstr: def _to_html(self): """Returns an html representation of the unicode string.""" html = "" - for c in escape(self.unicode): + for c in escape(self.raw): if c in "\t\r\n\r\f\a\b\v\0": esc_c = c.encode("unicode-escape").decode("utf8") html += '%s' % esc_c diff --git a/views/blob.html b/views/blob.html index 58c40a7..f1c6ad0 100644 --- a/views/blob.html +++ b/views/blob.html @@ -10,7 +10,7 @@ % relroot = reltree + '../' * (len(branch.split('/')) - 1) git » {{repo.name}} » - {{branch}} » {{dirname.unicode}}{{fname.unicode}} + {{branch}} » {{dirname.raw}}{{fname.raw}} {{c.unicode}} / + {{c.raw}} / % base += c + '/' % end {{!fname.html}} @@ -45,7 +45,7 @@ empty — 0 bytes -% elif can_embed_image(repo, fname.unicode): +% elif can_embed_image(repo, fname.raw): {{!embed_image_blob(fname.raw, blob.raw_content)}} % elif is_binary(blob.raw_content): @@ -72,12 +72,12 @@ % end
-% elif can_markdown(repo, fname.unicode): +% elif can_markdown(repo, fname.raw):
{{!markdown_blob(blob.utf8_content)}}
% elif can_colorize(blob.utf8_content): -{{!colorize_blob(fname.unicode, blob.utf8_content)}} +{{!colorize_blob(fname.raw, blob.utf8_content)}} % else:
 {{blob.utf8_content}}
diff --git a/views/tree.html b/views/tree.html
index 3f3829c..179672d 100644
--- a/views/tree.html
+++ b/views/tree.html
@@ -10,7 +10,7 @@
 % relroot = reltree + '../' * (len(branch.split('/')) - 1)
 
 git » {{repo.name}} »
-    {{branch}} » {{dirname.unicode if dirname.unicode else '/'}}
+    {{branch}} » {{dirname.raw if dirname.raw else '/'}}
 
 
@@ -31,7 +31,7 @@
 %   if not c.raw:
 %     continue
 %   end
-    {{c.unicode}} /
+    {{c.raw}} /
 %   base += c + '/'
 % end
 
-- 
cgit v1.2.3