1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247
|
#!/usr/bin/env python3
# Apache License, Version 2.0
"""
General purpose tool for remapping directory structure of RestructuredText documents.
This tool allows you to snapshot the structure, move files and directories about,
then finish the operation and all :doc:`... </path/to/file>` roles will be updated automatically.
Usage:
1) rst_remap.py start
2) # Reorganize the document structure, rename files.
3) rst_remap.py finish
note: you can't change the contents of the files you are remapping.
"""
import sys
import os
# -----------------------------------------------------------------------------
# Generic Functions
def uuid_from_file(fn, block_size=1 << 20):
"""
Returns an arbitrary sized unique ASCII string based on the file contents.
(exact hashing method may change).
"""
with open(fn, 'rb') as f:
# first get the size
import os
f.seek(0, os.SEEK_END)
size = f.tell()
f.seek(0, os.SEEK_SET)
del os
# done!
import hashlib
sha1 = hashlib.new('sha512')
while True:
data = f.read(block_size)
if not data:
break
sha1.update(data)
# skip the '0x'
return hex(size)[2:] + sha1.hexdigest()
# -----------------------------------------------------------------------------
# Command Line Interface
def fatal(msg):
if __name__ == "__main__":
sys.stderr.write("fatal: ")
sys.stderr.write(msg)
sys.stderr.write("\n")
sys.exit(1)
else:
raise RuntimeError(msg)
# if you want to operate on a subdir, e.g: "render"
SUBDIR = ""
CURRENT_DIR = os.path.abspath(os.path.dirname(__file__))
RST_DIR = os.path.normpath(os.path.join(CURRENT_DIR, "..", "..", "manual", SUBDIR))
# name for temp file
RST_MAP_ID = "rst_map.data"
def rst_files(path):
for dirpath, dirnames, filenames in os.walk(path):
if dirpath.startswith("."):
continue
for filename in filenames:
if filename.startswith("."):
continue
ext = os.path.splitext(filename)[1]
if ext.lower() == ".rst":
yield os.path.join(dirpath, filename)
def image_files(path):
for dirpath, dirnames, filenames in os.walk(path):
if dirpath.startswith("."):
continue
for filename in filenames:
ext = os.path.splitext(filename)[1]
if ext.lower() in {".jpg", ".jpeg", ".png", ".gif", ".svg", ".webp"}:
yield os.path.join(dirpath, filename)
def remap_data_create(base_path):
if os.sep != "/":
def compat_path(fn):
return "/" + fn.replace("\\", "/")
else:
def compat_path(fn):
return "/" + fn
# store rst's without extension
remap_rst = {}
for fn in rst_files(base_path):
file_hash = uuid_from_file(fn)
file_path = compat_path(os.path.splitext(
os.path.relpath(fn, base_path))[0])
file_path_prev = remap_rst.get(file_hash)
if file_path_prev is not None:
print("Duplicate file contents: %r, %r" %
(file_path_prev, file_path))
else:
remap_rst[file_hash] = file_path
# images keep their extension
remap_images = {}
for fn in image_files(base_path):
file_hash = uuid_from_file(fn)
file_path = compat_path(os.path.relpath(fn, base_path))
file_path_prev = remap_images.get(file_hash)
if file_path_prev is not None:
print("Duplicate file contents: %r, %r" %
(file_path_prev, file_path))
else:
remap_images[file_hash] = file_path
return (remap_rst, remap_images)
def remap_start(base_path):
filepath_remap = os.path.join(base_path, RST_MAP_ID)
if os.path.exists(filepath_remap):
fatal("Remap in progress, run with 'finish' or remove %r" %
filepath_remap)
remap_data_src = remap_data_create(base_path)
with open(filepath_remap, 'wb') as fh:
import pickle
pickle.dump(remap_data_src, fh, pickle.HIGHEST_PROTOCOL)
print("Remap started, tracking (%d rst, %d image) files." %
(len(remap_data_src[0]), len(remap_data_src[1])))
def remap_finish(base_path):
filepath_remap = os.path.join(base_path, RST_MAP_ID)
if not os.path.exists(filepath_remap):
fatal("Remap not started, run with 'start', (%r not found)" %
filepath_remap)
with open(filepath_remap, 'rb') as fh:
import pickle
remap_data_src = pickle.load(fh)
remap_data_dst = remap_data_create(base_path)
remap_rst_src, remap_image_src = remap_data_src
remap_rst_dst, remap_image_dst = remap_data_dst
remap_finish_rst(base_path, remap_rst_src, remap_rst_dst)
remap_finish_image(base_path, remap_image_src, remap_image_dst)
os.remove(filepath_remap)
def _src_dst_map(remap_src, remap_dst):
# Store: {source: dest}, without path prefix or extension, e.g:
# /path/to/docs/manual/interface/introduction.rst, becomes...
# /interface/introduction
src_dst_map = {}
for file_hash, file_path_src in remap_src.items():
file_path_dst = remap_dst.get(file_hash)
if file_path_dst is None:
# shouldn't happen often.
print("warning: source '%s' not found!" % file_path_src[1:])
file_path_dst = file_path_src
src_dst_map[file_path_src] = file_path_dst
if file_path_src.endswith("/index") and file_path_src != "/index":
src_dst_map[file_path_src[:-6]] = file_path_dst[:-6]
return src_dst_map
def remap_finish_rst(base_path, remap_rst_src, remap_rst_dst):
src_dst_map = _src_dst_map(remap_rst_src, remap_rst_dst)
# now remap the doc links
import rst_helpers
for fn in rst_files(base_path):
for d in rst_helpers.role_iter(fn, "doc", angle_brackets=True):
file_rstpath_src = d[-2].strip()
if "#" in file_rstpath_src:
file_rstpath_src, tail = file_rstpath_src.split("#", 1)
else:
tail = None
file_rstpath_dst = src_dst_map.get(file_rstpath_src)
if file_rstpath_dst is not None:
if tail is not None:
file_rstpath_dst = file_rstpath_dst + "#" + tail
d[-2] = file_rstpath_dst
else:
print("warning: unknown path %r" % file_rstpath_src)
def remap_finish_image(base_path, remap_image_src, remap_image_dst):
src_dst_map = _src_dst_map(remap_image_src, remap_image_dst)
# now remap the doc links
import rst_helpers
from itertools import chain
for fn in rst_files(base_path):
for d in chain(rst_helpers.directive_iter(fn, "figure"),
rst_helpers.directive_iter(fn, "image")):
file_imagepath_src = d[-1].strip()
file_imagepath_dst = src_dst_map.get(file_imagepath_src)
if file_imagepath_dst is not None:
d[-1] = file_imagepath_dst
else:
print("warning: unknown path %r" % file_imagepath_src)
def main(argv=sys.argv):
base_path = RST_DIR
if "start" in argv:
remap_start(base_path)
elif "finish" in argv:
remap_finish(base_path)
else:
print(__doc__)
print("Pass either 'start' or 'finish' as arguments")
if __name__ == "__main__":
main()
|