Merge branch 'master' into custom-shell

pudb/debugger.py

@@ -7,31 +7,16 @@ import bdb
 import gc
 import os
 import sys
+from functools import partial
 from types import TracebackType
 
+from pudb.lowlevel import decode_lines
 from pudb.settings import load_config, save_config
+from pudb.py3compat import PY3, raw_input, execfile
+
 CONFIG = load_config()
 save_config(CONFIG)
 
-from pudb.py3compat import PY3, raw_input, execfile
-if PY3:
-    _next = "__next__"
-else:
-    _next = "next"
-
-try:
-    from functools import partial
-except ImportError:
-    def partial(func, *args, **keywords):
-        def newfunc(*fargs, **fkeywords):
-            newkeywords = keywords.copy()
-            newkeywords.update(fkeywords)
-            return func(*(args + fargs), **newkeywords)
-        newfunc.func = func
-        newfunc.args = args
-        newfunc.keywords = keywords
-        return newfunc
-
 HELP_TEXT = """\
 Welcome to PuDB, the Python Urwid debugger.
 -------------------------------------------
@@ -555,10 +540,7 @@ class FileSourceCodeProvider(SourceCodeProvider):
         self.file_name = debugger.canonic(file_name)
 
     def __eq__(self, other):
-        return (
-                type(self) == type(other)
-                and
-                self.file_name == other.file_name)
+        return type(self) == type(other) and self.file_name == other.file_name
 
     def identifier(self):
         return self.file_name
@@ -585,18 +567,7 @@ class FileSourceCodeProvider(SourceCodeProvider):
         try:
             from linecache import getlines
             lines = getlines(self.file_name)
-
-            from pudb.lowlevel import detect_encoding
-            source_enc, _ = detect_encoding(getattr(iter(lines), _next))
-
-            decoded_lines = []
-            for l in lines:
-                if hasattr(l, "decode"):
-                    decoded_lines.append(l.decode(source_enc))
-                else:
-                    decoded_lines.append(l)
-
-            return format_source(debugger_ui, decoded_lines, set(breakpoints))
+            return format_source(debugger_ui, list(decode_lines(lines)), set(breakpoints))
         except:
             from pudb.lowlevel import format_exception
             debugger_ui.message("Could not load source file '%s':\n\n%s" % (
@@ -631,22 +602,8 @@ class DirectSourceCodeProvider(SourceCodeProvider):
     def get_lines(self, debugger_ui):
         from pudb.source_view import format_source
 
-        lines = self.code.split("\n")
-
-        from pudb.lowlevel import detect_encoding
-        source_enc, _ = detect_encoding(getattr(iter(lines), _next))
-
-        decoded_lines = []
-        for i, l in enumerate(lines):
-            if hasattr(l, "decode"):
-                l = l.decode(source_enc)
-
-            if i+1 < len(lines):
-                l += "\n"
-
-            decoded_lines.append(l)
-
-        return format_source(debugger_ui, decoded_lines, set())
+        lines = self.code.splitlines(True)
+        return format_source(debugger_ui, list(decode_lines(lines)), set())
 
 # }}}
 

pudb/lowlevel.py

@@ -86,7 +86,7 @@ def lookup_module(filename):
 
 
 # {{{ file encoding detection
-# stolen from Python 3.1's tokenize.py, by Ka-Ping Yee
+# the main idea stolen from Python 3.1's tokenize.py, by Ka-Ping Yee
 
 import re
 cookie_re = re.compile("^\s*#.*coding[:=]\s*([-\w.]+)")
@@ -95,13 +95,13 @@ if PY3:
     BOM_UTF8 = BOM_UTF8.decode()
 
 
-def detect_encoding(readline):
+def detect_encoding(lines):
     """
     The detect_encoding() function is used to detect the encoding that should
-    be used to decode a Python source file. It requires one argment, readline,
-    in the same way as the tokenize() generator.
+    be used to decode a Python source file. It requires one argment, lines,
+    iterable lines stream.
 
-    It will call readline a maximum of twice, and return the encoding used
+    It will read a maximum of two lines, and return the encoding used
     (as a string) and a list of any lines (left as bytes) it has read
     in.
 
@@ -113,11 +113,11 @@ def detect_encoding(readline):
     If no encoding is specified, then the default of 'utf-8' will be returned.
     """
     bom_found = False
-    encoding = None
+    line_iterator = iter(lines)
 
     def read_or_stop():
         try:
-            return readline()
+            return next(line_iterator)
         except StopIteration:
             return ''
 
@@ -166,6 +166,15 @@ def detect_encoding(readline):
 
     return 'utf-8', [first, second]
 
+
+def decode_lines(lines):
+    source_enc, _ = detect_encoding(lines)
+
+    for line in lines:
+        if hasattr(line, "decode"):
+            yield line.decode(source_enc)
+        else:
+            yield line
 # }}}
 
 

test/test_lowlevel.py

@@ -0,0 +1,31 @@
+# -*- coding: utf-8 -*-
+from pudb.lowlevel import detect_encoding, decode_lines
+from pudb.py3compat import PY3
+
+
+def test_detect_encoding_nocookie():
+    lines = ['Test Проверка']
+    encoding, _ = detect_encoding(lines)
+    assert encoding == 'utf-8'
+
+
+def test_detect_encoding_cookie():
+    lines = [
+        '# coding=utf-8',
+        'Test',
+        'Проверка'
+    ]
+    encoding, _ = detect_encoding(lines)
+    assert encoding == 'utf-8'
+
+
+def test_decode_lines():
+    lines = [
+        '# coding=utf-8',
+        'Test',
+        'Проверка',
+    ]
+    if PY3:
+        assert lines == list(decode_lines(lines))
+    else:
+        assert [l.decode('utf-8') for l in lines] == list(decode_lines(lines))

test/test_source_code_providers.py

@@ -0,0 +1,36 @@
+import pytest  # noqa: F401
+
+from pudb.debugger import NullSourceCodeProvider, FileSourceCodeProvider, DirectSourceCodeProvider
+from pudb.source_view import SourceLine
+
+
+class TestNullSourceCodeProvider:
+    def test_get_lines(self, mocker):
+        provider = NullSourceCodeProvider()
+        result = provider.get_lines(mocker.Mock())
+        assert len(result) == 10
+        assert isinstance(result[0], SourceLine)
+
+
+class TestFileSourceCodeProvider:
+    def test_string_file_name(self, mocker):
+        mock_debugger = mocker.Mock()
+        mock_debugger.canonic = mocker.Mock(return_value='<string>')
+        provider = FileSourceCodeProvider(mock_debugger, 'test file name')
+        result = provider.get_lines(mocker.MagicMock())
+        assert len(result) == 1
+        assert isinstance(result[0], SourceLine)
+
+    def test_get_lines(self, mocker):
+        provider = FileSourceCodeProvider(mocker.Mock(), 'test file name')
+        result = provider.get_lines(mocker.MagicMock())
+        assert len(result) == 1
+        assert isinstance(result[0], SourceLine)
+
+
+class TestDirectSourceCodeProvider:
+    def test_get_lines(self, mocker):
+        provider = DirectSourceCodeProvider(mocker.Mock(), 'test code')
+        result = provider.get_lines(mocker.Mock())
+        assert len(result) == 1
+        assert isinstance(result[0], SourceLine)