def main():
os.chdir(get_project_dir())
cell_types = set()
args = sys.argv[1:]
# XXX if both code and markdown should indent code 4 spaces as emitted
while args and args[0].startswith("-"):
arg = args[0]
del args[0]
if arg=="-c":
cell_types.add("code")
elif arg=="-m":
cell_types.add("markdown")
elif arg=="-h":
cell_types.add("heading")
else:
sys.exit("Usage: extract.py [-c] [-m] [-h] filename ...")
for src_file in args:
# Establish jinja templating environment (Do we even need to render?)
#template_env = Environment(loader=FileSystemLoader("data/templates"))
#src_template = template_env.get_template("markdown-only.ipynb")
now = datetime.datetime.today()
render_context = {"title": "Markdown extracted from "+os.path.abspath(src_file),
"date": now.date(),
"time": now.time(),
"src_file": src_file,
"template": "UNKNOWN"}
# All cells of the chosen type in the source notebook are copied across.
text_out = sys.stdout
src_nb = nbf.read(open(src_file, "r", encoding="UTF-8"), "ipynb")
# At present we don't render the extracted
# cell content, but that possibility remains open.
for worksheet in src_nb.worksheets:
cells_in = worksheet.cells
for cell in cells_in:
if cell.cell_type in cell_types:
if cell.cell_type == "code":
if "markdown" not in cell_types:
text_out.write(cell.input)
else:
text_out.write("".join(" "+line for line in cell.input.splitlines(keepends=True)))
elif cell.cell_type == "markdown":
text_out.write(cell.source)
elif cell.cell_type == "heading":
text_out.write("{} {}\n".format(
"#"*cell.level, cell.source))
else:
sys.exit("Should not have been called to process %s cells",
cell.cell_type)
text_out.write("\n\n")
text_out.close()
def mktopic(title):
"Takes a list of the words of a topic title and builds the appropriate notebook file."
os.chdir(lib.get_project_dir())
template_env = Environment(loader=FileSystemLoader("data/templates"))
# -t template would be nice, but this will do for now
src_template = template_env.get_template("base.ipynb")
now = datetime.datetime.today()
title = " ".join(title)
slug = lib.slugify(title)
nb_name = slug+".ipynb"
dst_file = os.path.join("nbsource", nb_name)
render_context = {"slug": slug,
"title": title,
"date": now.date(),
"time": now.time(),
"src_file": dst_file,
"template": src_template.filename} # we are writing a source ...
if os.path.isfile(dst_file):
# If the topic exists do not overwrite it XXX [unless option set].
sys.exit("file {} already exists".format(dst_file))
dst_nb_file = open(dst_file, "w")
nb_content = src_template.render(render_context)
dst_nb_file.write(nb_content)
dst_nb_file.close()
sys.exit("No notebooks with more than one cell")
totals = [0, 0, 0, 0, 0, 0]
format_str = "{:>{length}} {:4d} {:6,d} {:6,d} {:4d} {:6,d} {:6,d}"
format_hdr = "{:>{length}} {}"
print(format_hdr.format("", "------ code ------ ---- markdown ----", length=longest))
print(format_hdr.format("", "cells lines chars cells lines chars", length=longest))
for result in results:
result = list(result)
result[0] = result[0][:-6]
totals = [total+count for (total, count) in zip(totals, result[1:])]
print(format_str.
format(*result, length=longest))
print(format_str.format(*["TOTALS"]+totals, length=longest))
def get_lines_and_bytes(source):
lines = sum(l != "\n" for l in source)
bytes = sum(len(l) for l in source)
return lines, bytes
if __name__ == "__main__":
if len(sys.argv) == 1:
os.chdir(os.path.join(get_project_dir(), "nbsource"))
paths = glob("*.ipynb")
elif len(sys.argv) == 2 and os.path.isdir(sys.argv[1]):
os.chdir(sys.argv[1])
paths = glob("*.ipynb")
else:
paths = sys.argv[1:]
nbstats(paths)
"""Test topic matching and the like"""
import os
import unittest
import lib
import topics
os.chdir(lib.get_project_dir())
topic_list = topics.get_topics()
class TestMatching(unittest.TestCase):
def test_matching(self):
title_list = "the quick brown fox".split()
for word in title_list:
self.assertTrue(topics.matching(word, title_list))
for word in title_list:
self.assertTrue(topics.matching(word[1:-1], title_list))
self.assertTrue(topics.matching("", []))
self.assertTrue(topics.matching("unicode", ["unicode?"]))
if __name__ == "__main__":
unittest.main()
comment = " ***" if slug not in file_slugs else ""
print(os.path.join("project", "nbsource", slug + ".ipynb"), comment)
if __name__ == "__main__":
# possible -d option for directory?
exists = orphaned = False
# XXX one switch only ... use proper arg parsing
if len(sys.argv) > 1 and sys.argv[1][0] == "-":
if sys.argv[1] == "-u":
exists = True
elif sys.argv[1] == "-o":
orphaned = True
elif sys.argv[1] == "-a":
exists = None
else:
import sys
sys.exit("topics.py [-o | -u | -a] [List of words]")
del sys.argv[1]
os.chdir(get_project_dir())
if orphaned:
orphaned_topic_files()
else:
topic_list = slugify(" ".join(sys.argv[1:])).split("-")
# if topic_list == [""]: # Annoying special case?
# topic_list = []
topic_and_file(topic_list, exists=exists)
