Merge tag 'upstream/7.0.1'

Upstream version 7.0.1

1 files changed, 69 insertions, 51 deletions

diff --git a/nikola/winutils.py b/nikola/winutils.py
index 517a326..712de39 100644
--- a/nikola/winutils.py
+++ b/nikola/winutils.py
@@ -26,74 +26,92 @@
 
 """windows utilities to workaround problems with symlinks in a git clone"""
 
+from __future__ import print_function, unicode_literals
 import os
 import shutil
-import sys
-# don't add imports outside stdlib, will be imported in setup.py
+# don't add imports to nikola code, will be imported in setup.py
 
 
-def should_fix_git_symlinked():
-    """True if git symlinls markers should be filled with the real content"""
-    if sys.platform == 'win32':
-        path = (os.path.dirname(__file__) +
-                r'\data\samplesite\stories\theming.rst')
-        try:
-            if os.path.getsize(path) < 200:
-                return True
-        except Exception:
-            pass
-    return False
+def is_file_into_dir(filename, dirname):
+    try:
+        res = not os.path.relpath(filename, dirname).startswith('.')
+    except ValueError:
+        res = False
+    return res
 
 
-def fix_git_symlinked(src, dst):
-    """fix git symlinked files in windows that had been copied from src to dst
+def fix_all_git_symlinked(topdir):
+    """inplace conversion of git symlinks to real content
 
     Most (all?) of git implementations in windows store a symlink pointing
     into the repo as a text file, the text being the relative path to the
     file with the real content.
 
     So, in a clone of nikola in windows the symlinked files will have the
-    wrong content.
+    wrong content; a .zip download from Github has the same problem.
 
-    The linux usage pattern for those files is 'copy to some dir, then use',
-    so we inspect after the copy and rewrite the wrong contents.
+    This function will rewrite each symlinked file with the correct contents, but
+    keep in mind that the working copy will be seen as dirty by git after operation.
 
-    The goals are:
-       support running nikola from a clone without installing and without
-       making dirty the WC.
+    Expects to find a list of symlinked files at nikola/data/symlinked.txt
 
-       support install from the WC.
+    The list can be generated by scripts/generate_symlinked_list.sh , which is
+    basically a redirect of
+         cd nikola_checkout
+         git ls-files -s | awk '/120000/{print $4}'
 
-       if possible and needed, support running the test suite without making
-       dirty the WC.
+    Weakness: if interrupted of fail amidst a directory copy, next run will not
+    see the missing files.
     """
-    # if running from WC there should be a 'doc' dir sibling to nikola package
-    if not should_fix_git_symlinked():
-        return
-    # probabbly in a WC, so symlinks should be fixed
-    for root, dirs, files in os.walk(dst):
-        for name in files:
-            filename = os.path.join(root, name)
-
-            # detect if symlinked
-            try:
-                if not (2 < os.path.getsize(filename) < 500):
-                    continue
-                # which encoding uses a git symlink marker ? betting on default
-                with open(filename, 'r') as f:
-                    text = f.read()
-                if text[0] != '.':
-                    # de facto hint to skip binary files and exclude.meta
-                    continue
-            except Exception:
-                # probably encoding: content binary or encoding not defalt,
-                # also in py2.6 it can be path encoding
+    with open(topdir + r'\nikola\data\symlinked.txt', 'rb') as f:
+        all_bytes = f.read()
+        text = all_bytes.decode('utf8')
+    # expect each line a relpath from git or zip root,
+    # smoke test relpaths are relative to git root
+    if text.startswith('.'):
+        raise Exception(r'Bad data in \nikola\data\symlinked.txt')
+    relnames = text.split('\n')
+    relnames = [name.strip().replace('/', '\\') for name in relnames]
+    relnames = [name for name in relnames if name]
+
+    failures = 0
+    for name in relnames:
+        # build dst path and do some basic validation
+        dst = os.path.join(topdir, name)
+        # don't access files outside topdir
+        if not is_file_into_dir(dst, topdir):
+            continue
+        if os.path.isdir(dst):
+            # assume the file was de-symlinked
+            continue
+
+        # build src path and do some basic validation
+        with open(os.path.join(topdir, dst), 'r') as f:
+            text = f.read()
+        dst_dir = os.path.dirname(dst)
+        try:
+            src = os.path.normpath(os.path.join(dst_dir, text))
+            if not os.path.exists(src):
+                # assume the file was de-symlinked before
                 continue
-            dst_dir_relpath = os.path.dirname(os.path.relpath(filename, dst))
-            path = os.path.normpath(os.path.join(src, dst_dir_relpath, text))
-            if not os.path.exists(path):
+            # don't access files outside topdir
+            if not is_file_into_dir(src, topdir):
                 continue
-            # most probably it is a git symlinked file
+        except Exception:
+            # assume the file was de-symlinked before
+            continue
+
+        # copy src to dst
+        try:
+            if os.path.isdir(src):
+                os.unlink(dst)
+                shutil.copytree(src, dst)
+            else:
+                shutil.copy2(src, dst)
+        except Exception:
+            failures += 1
+            print("*** copy failed for")
+            print("\t src:", src)
+            print("\t dst:", dst)
 
-            # copy original content to filename
-            shutil.copy(path, filename)
+    return failures