new common.py

Akuli · Akuli · commit 04d459dfd5da · 2017-01-16T19:16:42.000+02:00
diff --git a/common.py b/common.py
@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+
+# This is free and unencumbered software released into the public
+# domain.
+
+# Anyone is free to copy, modify, publish, use, compile, sell, or
+# distribute this software, either in source code form or as a
+# compiled binary, for any purpose, commercial or non-commercial, and
+# by any means.
+
+# In jurisdictions that recognize copyright laws, the author or
+# authors of this software dedicate any and all copyright interest in
+# the software to the public domain. We make this dedication for the
+# benefit of the public at large and to the detriment of our heirs
+# and successors. We intend this dedication to be an overt act of
+# relinquishment in perpetuity of all present and future rights to
+# this software under copyright law.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY
+# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
+# CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+# For more information, please refer to <http://unlicense.org>
+
+"""Things that other scripts import and use."""
+
+import itertools
+import re
+import sys
+
+
+_LINK_REGEX = r'\[(.*?)\]\((.*?)\)'
+
+
+def find_links(file):
+    """Find all markdown links in a file object.
+
+    Yield (lineno, regexmatch) tuples.
+    """
+    # don't yield same link twice
+    seen = set()
+
+    # we need to loop over the file two lines at a time to support 
+    # multi-line (actually two-line) links, so this is kind of a mess
+    firsts, seconds = itertools.tee(file)
+    next(seconds)  # first line is never second line
+
+    # we want 1-based indexing instead of 0-based and one-line links get 
+    # caught from linepair[1], so we need to start at two
+    for lineno, linepair in enumerate(zip(firsts, seconds), start=2):
+        lines = linepair[0] + linepair[1]
+        for match in re.finditer(_LINK_REGEX, lines, flags=re.DOTALL):
+            if match.group(0) not in seen:
+                seen.add(match.group(0))
+                yield match, lineno
+
+
+def get_markdown_files():
+    """Yield the names of all markdown files in this tutorial.
+
+    This assumes that the README contains links to everything.
+    """
+    yield 'README.md'
+    with open('README.md', 'r') as f:
+        for match, lineno in find_links(f):
+            target = match.group(2)
+            # Currently the README doesn't link to itself, but I don't 
+            # want to break things if it will in the future.
+            if target.endswith('.md') and target != 'README.md':
+                yield target
+
+
+def askyesno(question, default=True):
+    """Ask a yes/no question and return True or False.
+
+    The default answer is yes if default is True and no if default is
+    False.
+    """
+    if default:
+        # yes by default
+        question += ' [Y/n] '
+    else:
+        # no by default
+        question += ' [y/N] '
+    while True:
+        result = input(question).upper().strip()
+        if result == 'Y':
+            return True
+        if result == 'N':
+            return False
+        if not result:
+            return default
diff --git a/make-html.py b/make-html.py
@@ -29,12 +29,13 @@
 """Create HTML files of the tutorial."""
 
 import os
-import re
 import shutil
 import string
 import sys
 import webbrowser
 
+import common
+
 try:
     import mistune
 except ImportError:
@@ -52,8 +53,6 @@
     pygments = None
 
 
-LINK_REGEX = r'\[.*\]\((.*\.md)\)'
-
 HTML_TEMPLATE = """\
 <!DOCTYPE html>
 <html>
@@ -68,30 +67,8 @@
 """
 
 
-def askyesno(question, default=True):
-    """Ask a yes/no question and return True or False.
-
-    The default answer is yes if default is True and no if default is
-    False.
-    """
-    if default:
-        # yes by default
-        question += ' [Y/n] '
-    else:
-        # no by default
-        question += ' [y/N] '
-    while True:
-        result = input(question).upper().strip()
-        if result == 'Y':
-            return True
-        if result == 'N':
-            return False
-        if not result:
-            return default
-
-
 def mkdir_open(filename, mode):
-    """Like built-in open(), but make a directory as needed."""
+    """Like open(), but make directories as needed."""
     directory = os.path.dirname(filename)
     os.makedirs(directory, exist_ok=True)
     return open(filename, mode)
@@ -204,25 +181,21 @@ def main():
         print()
         print("You can also continue without Pygments, but the code examples")
         print("will not be in color.")
-        if not askyesno("Continue without pygments?"):
+        if not common.askyesno("Continue without pygments?"):
             print("Interrupt.")
             return
 
     if os.path.exists('html'):
-        if not askyesno("html exists. Do you want to remove it?"):
+        if not common.askyesno("html exists. Do you want to remove it?"):
             print("Interrupt.")
             return
         if os.path.isdir('html'):
             shutil.rmtree('html')
         else:
             os.remove('html')
 
-    print("Getting a list of files to generate...")
-    with open('README.md', 'r') as f:
-        filelist = re.findall(LINK_REGEX, f.read()) + ['README.md']
-
     print("Generating HTML files...")
-    for markdownfile in filelist:
+    for markdownfile in common.get_markdown_files():
         htmlfile = os.path.join('html', fix_filename(markdownfile))
         print(' ', markdownfile, '->', htmlfile)
         with open(markdownfile.replace('/', os.sep), 'r') as f:
@@ -241,7 +214,7 @@ def main():
     print("Ready! The files are in the html directory.")
     print("Go to html and double-click index.html to read the tutorial.")
     print()
-    if askyesno("Do you want to view the tutorial now?", default=False):
+    if common.askyesno("Do you want to view the tutorial now?", default=False):
         print("Opening the tutorial...")
         webbrowser.open(os.path.join('html', 'index.html'))
 
diff --git a/update-ends.py b/update-ends.py
@@ -28,12 +28,13 @@
 
 """Update ends of markdown files."""
 
-import os
 import re
 
+import common
+
 
 # Markdown and HTML links use / as a path separator so there's no need 
-# for os.path, but we do need to replace it with os.sep when opening the 
+# for os.path, but we do need to replace / with os.sep when opening the 
 # files.
 BASIC_END = """\
 You may use this tutorial freely at your own risk. See
@@ -51,8 +52,7 @@
 """
 
 
-LINK_REGEX = r'\[.*\]\((.*\.md)\)'
-CHAPTER_LINK_REGEX = r'^\d+\. ' + LINK_REGEX + r'$'
+CHAPTER_LINK_REGEX = r'^\d+\. \[.*\]\((.*\.md)\)$'
 
 
 def get_filenames():
@@ -80,11 +80,7 @@ def get_filenames():
                     # it's a link to a chapter
                     chapters.append(match.group(1))
 
-    # now let's find other links to markdown files
-    with open('README.md', 'r') as f:
-        all_files = re.findall(LINK_REGEX, f.read())
-    others = set(all_files) - set(chapters)
-
+    others = set(common.get_markdown_files()) - set(chapters)
     return chapters, others
 
 
@@ -156,7 +152,7 @@ def main():
 
     print("Other files:")
     for filename in other_files:
-        end = BASIC_END.format(toplevel='../' * filename.count('/'))
+        end = BASIC_END.format(toplevel='../'*filename.count('/'))
         update_end(filename, end)
 
 
