organicmaps/mwm.py
13
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity Actions

Initial commit, transferred from the omim repository

Browse source
This commit is contained in:
Ilya Zverev 2017-04-11 12:47:20 +03:00
commit 49b5652213
10 changed files with 865 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
.gitignore vendored Normal file
View file

@ -0,0 +1,3 @@
build/
__pycache__/
*.pyc

175
LICENSE Normal file
View file

@ -0,0 +1,175 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.

31
README.md Normal file
View file

@ -0,0 +1,31 @@
# mwm.py
It is a python library to read contents of MAPS.ME mwm files. Not everything
is supported, but you can get at least all the features and their attributes.
We at MAPS.ME use this script to do analytics and maintenance.
## Installation
pip install mwm
## Usage
Just add `import mwm` to your script, and read an mwm file with:
```python
with open('file.mwm', 'rb') as f:
data = mwm.MWM(f)
```
## Tools
There are some useful tools in the relevant directory, which can serve as
the library usage examples:
* `dump_mwm.py` prints the header and some statistics on an mwm file.
* `find_feature.py` can find features inside an mwm by type or name.
* `ft2osm.py` converts a feature id to an OSM website link.
## License
Written by Ilya Zverev for MAPS.ME. Published under the Apache License 2.0.

2
mwm/__init__.py Normal file
View file

@ -0,0 +1,2 @@
from .mwm import MWM, Osm2Ft
from .mwmfile import MWMFile

305
mwm/mwm.py Normal file
View file

@ -0,0 +1,305 @@
# MWM Reader Module
from .mwmfile import MWMFile
from datetime import datetime
# Unprocessed sections: geomN, trgN, idx, sdx (search index), addr (search address), offs (feature offsets - succinct)
# Routing sections: mercedes (matrix), daewoo (edge data), infinity (edge id), skoda (shortcuts), chrysler (cross context), ftseg, node2ftseg
# (these mostly are succinct structures, except chrysler and node2ftseg, so no use trying to load them here)
# TODO:
# - Predictive reading of LineStrings
# - Find why polygon geometry is incorrect in iter_features()
# - Find feature ids in the 'dat' section, or find a way to read the 'offs' section
class MWM(MWMFile):
# indexer/feature_meta.hpp
metadata = ["0",
"cuisine", "open_hours", "phone_number", "fax_number", "stars",
"operator", "url", "website", "internet", "ele",
"turn_lanes", "turn_lanes_forward", "turn_lanes_backward", "email", "postcode",
"wikipedia", "maxspeed", "flats", "height", "min_height",
"denomination", "building_levels", "test_id", "ref:sponsored", "price_rate",
"rating", "fuel", "routes"]
regiondata = ["languages", "driving", "timezone", "addr_fmt", "phone_fmt", "postcode_fmt", "holidays", "housenames"]
def __init__(self, f):
MWMFile.__init__(self, f)
self.read_tags()
self.read_header()
self.type_mapping = []
def read_types(self, filename):
with open(filename, 'r') as ft:
for line in ft:
if len(line.strip()) > 0:
self.type_mapping.append(line.strip().replace('|', '-'))
def read_version(self):
"""Reads 'version' section."""
self.seek_tag('version')
self.f.read(4) # skip prolog
fmt = self.read_varuint() + 1
version = self.read_varuint()
if version < 161231:
version = datetime(2000 + int(version / 10000), int(version / 100) % 100, version % 100)
else:
version = datetime.fromtimestamp(version)
return {'fmt': fmt, 'version': version}
def read_header(self):
"""Reads 'header' section."""
if not self.has_tag('header'):
# Stub for routing files
self.coord_size = (1 << 30) - 1
return {}
self.seek_tag('header')
result = {}
coord_bits = self.read_varuint()
self.coord_size = (1 << coord_bits) - 1
self.base_point = self.mwm_bitwise_split(self.read_varuint())
result['basePoint'] = self.to_4326(self.base_point)
result['bounds'] = self.read_bounds()
result['scales'] = self.read_uint_array()
langs = self.read_uint_array()
for i in range(len(langs)):
if i < len(self.languages):
langs[i] = self.languages[langs[i]]
result['langs'] = langs
map_type = self.read_varint()
if map_type == 0:
result['mapType'] = 'world'
elif map_type == 1:
result['mapType'] = 'worldcoasts'
elif map_type == 2:
result['mapType'] = 'country'
else:
result['mapType'] = 'unknown: {0}'.format(map_type)
return result
# COMPLEX READERS
def read_region_info(self):
if not self.has_tag('rgninfo'):
return {}
fields = {}
self.seek_tag('rgninfo')
sz = self.read_varuint()
if sz:
for i in range(sz):
t = self.read_varuint()
t = self.regiondata[t] if t < len(self.regiondata) else str(t)
fields[t] = self.read_string()
if t == 'languages':
fields[t] = [self.languages[ord(x)] for x in fields[t]]
return fields
def read_metadata(self):
"""Reads 'meta' and 'metaidx' sections."""
if not self.has_tag('metaidx'):
return {}
# Metadata format is different since v8
fmt = self.read_version()['fmt']
# First, read metaidx, to match featureId <-> metadata
self.seek_tag('metaidx')
ftid_meta = []
while self.inside_tag('metaidx'):
ftid = self.read_uint(4)
moffs = self.read_uint(4)
ftid_meta.append((moffs, ftid))
# Sort ftid_meta array
ftid_meta.sort(key=lambda x: x[0])
ftpos = 0
# Now read metadata
self.seek_tag('meta')
metadatar = {}
while self.inside_tag('meta'):
tag_pos = self.tag_offset('meta')
fields = {}
if fmt >= 8:
sz = self.read_varuint()
if sz:
for i in range(sz):
t = self.read_varuint()
t = self.metadata[t] if t < len(self.metadata) else str(t)
fields[t] = self.read_string()
if t == 'fuel':
fields[t] = fields[t].split('\x01')
else:
while True:
t = self.read_uint(1)
is_last = t & 0x80 > 0
t = t & 0x7f
t = self.metadata[t] if t < len(self.metadata) else str(t)
l = self.read_uint(1)
fields[t] = self.f.read(l).decode('utf-8')
if is_last:
break
if len(fields):
while ftpos < len(ftid_meta) and ftid_meta[ftpos][0] < tag_pos:
ftpos += 1
if ftpos < len(ftid_meta):
if ftid_meta[ftpos][0] == tag_pos:
metadatar[ftid_meta[ftpos][1]] = fields
return metadatar
def read_crossmwm(self):
"""Reads 'chrysler' section (cross-mwm routing table)."""
if not self.has_tag('chrysler'):
return {}
self.seek_tag('chrysler')
# Ingoing nodes: array of (nodeId, coord) tuples
incomingCount = self.read_uint(4)
incoming = []
for i in range(incomingCount):
nodeId = self.read_uint(4)
point = self.read_coord(False)
incoming.append((nodeId, point))
# Outgoing nodes: array of (nodeId, coord, outIndex) tuples
# outIndex is an index in neighbours array
outgoingCount = self.read_uint(4)
outgoing = []
for i in range(outgoingCount):
nodeId = self.read_uint(4)
point = self.read_coord(False)
outIndex = self.read_uint(1)
outgoing.append((nodeId, point, outIndex))
# Adjacency matrix: costs of routes for each (incoming, outgoing) tuple
matrix = []
for i in range(incomingCount):
sub = []
for j in range(outgoingCount):
sub.append(self.read_uint(4))
matrix.append(sub)
# List of mwms to which leads each outgoing node
neighboursCount = self.read_uint(4)
neighbours = []
for i in range(neighboursCount):
size = self.read_uint(4)
neighbours.append(self.f.read(size).decode('utf-8'))
return {'in': incoming, 'out': outgoing, 'matrix': matrix, 'neighbours': neighbours}
def iter_features(self, metadata=False):
"""Reads 'dat' section."""
if not self.has_tag('dat'):
return
# TODO: read 'offs'?
md = {}
if metadata:
md = self.read_metadata()
self.seek_tag('dat')
ftid = -1
while self.inside_tag('dat'):
ftid += 1
feature = {'id': ftid}
feature_size = self.read_varuint()
next_feature = self.f.tell() + feature_size
feature['size'] = feature_size
# Header
header = {}
header_bits = self.read_uint(1)
types_count = (header_bits & 0x07) + 1
has_name = header_bits & 0x08 > 0
has_layer = header_bits & 0x10 > 0
has_addinfo = header_bits & 0x80 > 0
geom_type = header_bits & 0x60
types = []
for i in range(types_count):
type_id = self.read_varuint()
if type_id < len(self.type_mapping):
types.append(self.type_mapping[type_id])
else:
types.append(str(type_id + 1)) # So the numbers match with mapcss-mapping.csv
header['types'] = types
if has_name:
header['name'] = self.read_multilang()
if has_layer:
header['layer'] = self.read_uint(1)
if has_addinfo:
if geom_type == MWM.GeomType.POINT:
header['rank'] = self.read_uint(1)
elif geom_type == MWM.GeomType.LINE:
header['ref'] = self.read_string()
elif geom_type == MWM.GeomType.AREA or geom_type == MWM.GeomType.POINT_EX:
header['house'] = self.read_numeric_string()
feature['header'] = header
# Metadata
if ftid in md:
feature['metadata'] = md[ftid]
# Geometry
geometry = {}
if geom_type == MWM.GeomType.POINT or geom_type == MWM.GeomType.POINT_EX:
geometry['type'] = 'Point'
elif geom_type == MWM.GeomType.LINE:
geometry['type'] = 'LineString'
elif geom_type == MWM.GeomType.AREA:
geometry['type'] = 'Polygon'
if geom_type == MWM.GeomType.POINT:
geometry['coordinates'] = list(self.read_coord())
# (flipping table emoticon)
feature['geometry'] = geometry
if False:
if geom_type != MWM.GeomType.POINT:
polygon_count = self.read_varuint()
polygons = []
for i in range(polygon_count):
count = self.read_varuint()
buf = self.f.read(count)
# TODO: decode
geometry['coordinates'] = polygons
feature['coastCell'] = self.read_varint()
# OSM IDs
count = self.read_varuint()
osmids = []
for i in range(count):
osmid = self.read_osmid()
osmids.append('{0}{1}'.format(osmid[0], osmid[1]))
feature['osmIds'] = osmids
if self.f.tell() > next_feature:
raise Exception('Feature parsing error, read too much')
yield feature
self.f.seek(next_feature)
class Osm2Ft(MWMFile):
def __init__(self, f, ft2osm=False, tuples=True):
MWMFile.__init__(self, f)
self.read(ft2osm, tuples)
def read(self, ft2osm=False, tuples=True):
"""Reads mwm.osm2ft file, returning a dict of feature id <-> osm way id."""
count = self.read_varuint()
self.data = {}
self.ft2osm = ft2osm
for i in range(count):
osmid = self.read_osmid(tuples)
fid = self.read_uint(4)
self.read_uint(4) # filler
if osmid is not None:
if ft2osm:
self.data[fid] = osmid
else:
self.data[osmid] = fid
def __getitem__(self, k):
return self.data.get(k)
def __repr__(self):
return '{} with {} items'.format('ft2osm' if self.ft2osm else 'osm2ft', len(self.data))
def __len__(self):
return len(self.data)
def __contains__(self, k):
return k in self.data
def __iter__(self):
return iter(self.data)

218
mwm/mwmfile.py Normal file
View file

@ -0,0 +1,218 @@
# MWM Reader Module
import struct
import math
class MWMFile(object):
# coding/multilang_utf8_string.cpp
languages = ["default",
"en", "ja", "fr", "ko_rm", "ar", "de", "int_name", "ru", "sv", "zh", "fi", "be", "ka", "ko",
"he", "nl", "ga", "ja_rm", "el", "it", "es", "zh_pinyin", "th", "cy", "sr", "uk", "ca", "hu",
"hsb", "eu", "fa", "br", "pl", "hy", "kn", "sl", "ro", "sq", "am", "fy", "cs", "gd", "sk",
"af", "ja_kana", "lb", "pt", "hr", "fur", "vi", "tr", "bg", "eo", "lt", "la", "kk", "gsw",
"et", "ku", "mn", "mk", "lv", "hi"]
def __init__(self, f):
self.f = f
self.tags = {}
self.coord_size = None
self.base_point = (0, 0)
def read_tags(self):
self.f.seek(0)
self.f.seek(self.read_uint(8))
cnt = self.read_varuint()
for i in range(cnt):
name = self.read_string(plain=True)
offset = self.read_varuint()
length = self.read_varuint()
self.tags[name] = (offset, length)
def has_tag(self, tag):
return tag in self.tags and self.tags[tag][1] > 0
def seek_tag(self, tag):
self.f.seek(self.tags[tag][0])
def tag_offset(self, tag):
return self.f.tell() - self.tags[tag][0]
def inside_tag(self, tag):
pos = self.tag_offset(tag)
return pos >= 0 and pos < self.tags[tag][1]
def read_uint(self, bytelen=1):
if bytelen == 1:
fmt = 'B'
elif bytelen == 2:
fmt = 'H'
elif bytelen == 4:
fmt = 'I'
elif bytelen == 8:
fmt = 'Q'
else:
raise Exception('Bytelen {0} is not supported'.format(bytelen))
res = struct.unpack(fmt, self.f.read(bytelen))
return res[0]
def read_varuint(self):
res = 0
shift = 0
more = True
while more:
b = self.f.read(1)
if not b:
return res
try:
bc = ord(b)
except TypeError:
bc = b
res |= (bc & 0x7F) << shift
shift += 7
more = bc >= 0x80
return res
@staticmethod
def zigzag_decode(uint):
res = uint >> 1
return res if uint & 1 == 0 else -res
def read_varint(self):
return self.zigzag_decode(self.read_varuint())
class GeomType:
POINT = 0
LINE = 1 << 5
AREA = 1 << 6
POINT_EX = 3 << 5
class OsmIdCode:
NODE = 0x4000000000000000
WAY = 0x8000000000000000
RELATION = 0xC000000000000000
RESET = ~(NODE | WAY | RELATION)
@staticmethod
def unpack_osmid(num):
if num & MWMFile.OsmIdCode.NODE == MWMFile.OsmIdCode.NODE:
typ = 'n'
elif num & MWMFile.OsmIdCode.WAY == MWMFile.OsmIdCode.WAY:
typ = 'w'
elif num & MWMFile.OsmIdCode.RELATION == MWMFile.OsmIdCode.RELATION:
typ = 'r'
else:
return None
return typ, num & MWMFile.OsmIdCode.RESET
def read_osmid(self, as_tuple=True):
osmid = self.read_uint(8)
return self.unpack_osmid(osmid) if as_tuple else osmid
def mwm_unshuffle(self, x):
x = ((x & 0x22222222) << 1) | ((x >> 1) & 0x22222222) | (x & 0x99999999)
x = ((x & 0x0C0C0C0C) << 2) | ((x >> 2) & 0x0C0C0C0C) | (x & 0xC3C3C3C3)
x = ((x & 0x00F000F0) << 4) | ((x >> 4) & 0x00F000F0) | (x & 0xF00FF00F)
x = ((x & 0x0000FF00) << 8) | ((x >> 8) & 0x0000FF00) | (x & 0xFF0000FF)
return x
def mwm_bitwise_split(self, v):
hi = self.mwm_unshuffle(v >> 32)
lo = self.mwm_unshuffle(v & 0xFFFFFFFF)
x = ((hi & 0xFFFF) << 16) | (lo & 0xFFFF)
y = (hi & 0xFFFF0000) | (lo >> 16)
return (x, y)
def mwm_decode_delta(self, v, ref):
x, y = self.mwm_bitwise_split(v)
return ref[0] + self.zigzag_decode(x), ref[1] + self.zigzag_decode(y)
def read_point(self, ref, packed=True):
"""Reads an unsigned point, returns (x, y)."""
if packed:
u = self.read_varuint()
else:
u = self.read_uint(8)
return self.mwm_decode_delta(u, ref)
def to_4326(self, point):
"""Convert a point in maps.me-mercator CS to WGS-84 (EPSG:4326)."""
if self.coord_size is None:
raise Exception('Call read_header() first.')
merc_bounds = (-180.0, -180.0, 180.0, 180.0) # Xmin, Ymin, Xmax, Ymax
x = point[0] * (merc_bounds[2] - merc_bounds[0]) / self.coord_size + merc_bounds[0]
y = point[1] * (merc_bounds[3] - merc_bounds[1]) / self.coord_size + merc_bounds[1]
y = 360.0 * math.atan(math.tanh(y * math.pi / 360.0)) / math.pi
return (x, y)
def read_coord(self, packed=True):
"""Reads a pair of coords in degrees mercator, returns (lon, lat)."""
point = self.read_point(self.base_point, packed)
return self.to_4326(point)
def read_bounds(self):
"""Reads mercator bounds, returns (min_lon, min_lat, max_lon, max_lat)."""
rmin = self.mwm_bitwise_split(self.read_varint())
rmax = self.mwm_bitwise_split(self.read_varint())
pmin = self.to_4326(rmin)
pmax = self.to_4326(rmax)
return (pmin[0], pmin[1], pmax[0], pmax[1])
def read_string(self, plain=False, decode=True):
length = self.read_varuint() + (0 if plain else 1)
s = self.f.read(length)
return s.decode('utf-8') if decode else s
def read_uint_array(self):
length = self.read_varuint()
result = []
for i in range(length):
result.append(self.read_varuint())
return result
def read_numeric_string(self):
sz = self.read_varuint()
if sz & 1 != 0:
return str(sz >> 1)
sz = (sz >> 1) + 1
return self.f.read(sz).decode('utf-8')
def read_multilang(self):
def find_multilang_next(s, i):
i += 1
while i < len(s):
try:
c = ord(s[i])
except:
c = s[i]
if c & 0xC0 == 0x80:
break
if c & 0x80 == 0:
pass
elif c & 0xFE == 0xFE:
i += 6
elif c & 0xFC == 0xFC:
i += 5
elif c & 0xF8 == 0xF8:
i += 4
elif c & 0xF0 == 0xF0:
i += 3
elif c & 0xE0 == 0xE0:
i += 2
elif c & 0xC0 == 0xC0:
i += 1
i += 1
return i
s = self.read_string(decode=False)
langs = {}
i = 0
while i < len(s):
n = find_multilang_next(s, i)
try:
lng = ord(s[i]) & 0x3F
except TypeError:
lng = s[i] & 0x3F
if lng < len(self.languages):
langs[self.languages[lng]] = s[i+1:n].decode('utf-8')
i = n
return langs

28
setup.py Normal file
View file

@ -0,0 +1,28 @@
from setuptools import setup
from os import path
here = path.abspath(path.dirname(__file__))
setup(
name='mwm',
version='0.9.0',
author='Ilya Zverev',
author_email='ilya@zverev.info',
packages=['mwm'],
url='http://pypi.python.org/pypi/mwm/',
license='Apache License 2.0',
description='Library to read binary MAPS.ME files.',
long_description=open(path.join(here, 'README.md')).read(),
classifiers=[
'Development Status :: 4 - Beta',
'Intended Audience :: Developers',
'Topic :: Software Development :: Libraries :: Python Modules',
'Topic :: Utilities',
'Environment :: Console',
'License :: OSI Approved :: Apache Software License',
'Programming Language :: Python',
'Programming Language :: Python :: 2.6',
'Programming Language :: Python :: 2.7',
'Programming Language :: Python :: 3',
],
)

40
tools/dump_mwm.py Executable file
View file

@ -0,0 +1,40 @@
#!/usr/bin/python
import sys, os.path, random
import json
from mwm import MWM
if len(sys.argv) < 2:
print('Dumps some MWM structures.')
print('Usage: {0} <country.mwm>'.format(sys.argv[0]))
sys.exit(1)
mwm = MWM(open(sys.argv[1], 'rb'))
mwm.read_types(os.path.join(os.path.dirname(sys.argv[0]), '..', '..', '..', '..', 'data', 'types.txt'))
print('Tags:')
tvv = sorted([(k, v[0], v[1]) for k, v in mwm.tags.items()], key=lambda x: x[1])
for tv in tvv:
print(' {0:<8}: offs {1:9} len {2:8}'.format(tv[0], tv[1], tv[2]))
v = mwm.read_version()
print('Format: {0}, version: {1}'.format(v['fmt'], v['version'].strftime('%Y-%m-%d %H:%M')))
print('Header: {0}'.format(mwm.read_header()))
print('Region Info: {0}'.format(mwm.read_region_info()))
print('Metadata count: {0}'.format(len(mwm.read_metadata())))
cross = mwm.read_crossmwm()
if cross:
print('Outgoing points: {0}, incoming: {1}'.format(len(cross['out']), len(cross['in'])))
print('Outgoing regions: {0}'.format(set(cross['neighbours'])))
# Print some random features using reservoir sampling
count = 5
sample = []
for i, feature in enumerate(mwm.iter_features()):
if i < count:
sample.append(feature)
elif random.randint(0, i) < count:
sample[random.randint(0, count-1)] = feature
print('Feature count: {0}'.format(i))
print('Sample features:')
for feature in sample:
print(json.dumps(feature, ensure_ascii=False))

41
tools/find_feature.py Executable file
View file

@ -0,0 +1,41 @@
#!/usr/bin/env python
import sys, os.path, json
from mwm import MWM
if len(sys.argv) < 4:
print('Finds features in an mwm file based on a query')
print('Usage: {0} <country.mwm> <type> <string>'.format(sys.argv[0]))
print('')
print('Type:')
print(' t for inside types ("t hwtag" will find all hwtags-*)')
print(' et for exact type ("et shop" won\'t find shop-chemist)')
print(' n for names, case-sensitive ("n Starbucks" for all starbucks)')
print(' m for metadata keys ("m flats" for features with flats)')
print(' id for feature id ("id 1234" for feature #1234)')
sys.exit(1)
typ = sys.argv[2].lower()
find = sys.argv[3].decode('utf-8')
mwm = MWM(open(sys.argv[1], 'rb'))
mwm.read_header()
mwm.read_types(os.path.join(os.path.dirname(sys.argv[0]), '..', '..', '..', '..', 'data', 'types.txt'))
for i, feature in enumerate(mwm.iter_features(metadata=True)):
found = False
if typ == 'n' and 'name' in feature['header']:
for value in feature['header']['name'].values():
if find in value:
found = True
elif typ in ('t', 'et'):
for t in feature['header']['types']:
if t == find:
found = True
elif typ == 't' and find in t:
found = True
elif typ == 'm' and 'metadata' in feature:
if find in feature['metadata']:
found = True
elif typ == 'id' and i == int(find):
found = True
if found:
print(json.dumps(feature, ensure_ascii=False, sort_keys=True).encode('utf-8'))

22
tools/ft2osm.py Executable file
View file

@ -0,0 +1,22 @@
#!/usr/bin/env python
import sys
import mwm
if len(sys.argv) < 3:
print('Finds an OSM object for a given feature id.')
print('Usage: {} <mwm.osm2ft> <ftid>'.format(sys.argv[0]))
sys.exit(1)
with open(sys.argv[1], 'rb') as f:
ft2osm = mwm.Osm2Ft(f, True)
code = 0
type_abbr = {'n': 'node', 'w': 'way', 'r': 'relation'}
for ftid in sys.argv[2:]:
ftid = int(ftid)
if ftid in ft2osm:
print('https://www.openstreetmap.org/{}/{}'.format(type_abbr[ft2osm[ftid][0]], ft2osm[ftid][1]))
else:
print('Could not find osm id for feature {}'.format(ftid))
code = 2
sys.exit(code)