update geo tools

This commit is contained in:
rlx 2011-09-09 16:40:04 +00:00
parent 7035e207c2
commit 204f083e98
2 changed files with 346 additions and 17 deletions

View file

@ -64,7 +64,7 @@
<script>
/*
this adds the properties
area, east, imageURL, lat, lng, north, south, west
area, east, lat, lng, north, south, west
*/
Ox.load('UI', {debug: true}, function() {
Ox.getJSON('../json/geo.json', function(geo) {
@ -222,8 +222,11 @@
var addresses = geo.google_query[country.name] || [country.name],
length = addresses.length,
union;
// fixme: this might be too much data
// check if map really needs this preloaded
// (and even if, country markers may not be necessary)
getImageURLs(country, function(imageURLs) {
$.extend(country, {
Ox.extend(country, {
imageURLs: imageURLs
});
callGeocode();
@ -273,14 +276,14 @@
}
}
function getImageURLs(country, callback) {
Ox.print(country, '../png/marker/32/' + country.code + '.png')
Ox.print(country, '../png/icon/16/' + country.code + '.png')
var image = new Image();
image.onload = function() {
callback({
marker: Ox.canvas(image).canvas.toDataURL()
icon16: Ox.canvas(image).canvas.toDataURL()
});
};
image.src = '../png/markers/32/' + country.code + '.png';
image.src = '../png/icons/16/' + country.code + '.png';
}
});
});

View file

@ -222,7 +222,7 @@ geo = {
'Diego Garcia': 'Flag_of_the_British_Indian_Ocean_Territory.svg',
'French Guiana': 'Flag_of_French_Guiana.svg',
'Korea': 'Flag_of_Korea_1882.svg',
'Libya': 'Flag_of_the_Libyan_Jamahiriya_1977.svg',
# 'Libya': 'Flag_of_the_Libyan_Jamahiriya_1977.svg',
'Metropolitan France': 'Flag_of_France.svg',
'Neutral Zone': 'Flag_of_the_United_Nations.svg',
'New Hebrides': 'Flag_of_Anglo-French_Joint_Naval_Commission.svg',
@ -260,7 +260,7 @@ geo = {
'Curaçao': ['Banda Abou, Curaçao'],
'Czechoslovakia': ['Czech Republic', 'Slovakia'],
'East Germany': [
'Brandenburg', 'Mecklenburg Vorpommern', 'Saxony', 'Saxony Anhalt', 'Thuringia'
'Mecklenburg Vorpommern', 'Saxony', 'Thuringia'
],
'Dahomey': ['Benin'],
'European Union': ['Europe'],
@ -303,14 +303,15 @@ geo = {
'Latvia', 'Lithuania', 'Kazakhstan', 'Kyrgyzstan', 'Moldova',
'Russia', 'Tajikistan', 'Turkmenistan', 'Ukraine', 'Uzbekistan'
],
'United Kingdom': ['England', 'Northern Ireland', 'Scotland', 'Wales'],
'United Kingdom': ['England', 'Northern Ireland', 'Scotland', 'Wales, United Kingdom'],
'United States Minor Outlying Islands': ['Midway Islands'],
# Baker Island, Howland Island, Jarvis Island, Kingman Reef, Palmyra Atoll --
# but the first three each return the full United States Minor Outlying Islands
'United States Miscellaneous Pacific Islands': ['Kingman Reef', 'Palmyra Atoll'],
'UK': ['England', 'Northern Ireland', 'Scotland', 'Wales'],
'UK': ['England', 'Northern Ireland', 'Scotland', 'Wales, United Kingdom'],
'Upper Volta': ['Burkina Faso'],
'Wake Island': ['Wake Atoll'],
'Wales': ['Wales, United Kingdom'],
'West Germany': ['Schleswig Holstein', 'Northrhine Westphalia', 'Bavaria, Germany'],
'Yugoslavia': [
'Bosnia and Herzegovina', 'Croatia', 'Serbia', 'Slovenia', 'Macedonia',
@ -634,6 +635,324 @@ geo = {
'ZRCD': 'crop()',
'ZW': 'crop(left)'
},
# import json
# import re
# from ox.net import readUrl
# html = readUrl('http://www.imdb.com/language/')
# results = re.compile(re.compile('<a href="/language/.*?">(.*?)</a>').findall(html))
# languages = {}
# for result in results:
# languages[result] = ''
# print json.dumps(languages, sort_keys=True)
# http://www.imdb.com/language/
'languages': {
'Abkhazian': 'Abkhazia',
'Aboriginal': 'Australia',
'Aché': '',
'Acholi': '',
'Afrikaans': 'South Africa',
'Aidoukrou': '',
'Akan': '',
'Albanian': 'Albania',
'Algonquin': '',
'American': 'United States',
'Amharic': '',
'Apache': '',
'Arabic': 'Saudi Arabia',
'Aragonese': '',
'Aramaic': 'Syria',
'Arapaho': '',
'Armenian': 'Armenia',
'Assamese': 'India',
'Assyrian Neo-Aramaic': '',
'Athapascan': '',
'Australian': 'Australia',
'Awadhi': '',
'Aymara': 'Bolivia',
'Azerbaijani': 'Azerbaijan',
'Bable': '',
'Baka': '',
'Balinese': 'Indonesia',
'Bambara': 'Mali',
'Basque': '',
'Bassari': '',
'Belarusian': 'Belarus',
'Bemba': '',
'Bengali': 'Bangladesh',
'Berber': '',
'Bhojpuri': '',
'Bicolano': 'Philippines',
'Bodo': '',
'Bosnian': 'Bosnia and Herzegovina',
'Brazilian': 'Brazil',
'Breton': 'France',
'British': 'United Kingdom',
'Bulgarian': 'Bulgaria',
'Burmese': 'Burma',
'Cantonese': 'China',
'Catalan': 'Spain',
'Central Khmer': 'Cambodia',
'Chaozhou': '',
'Chechen': 'Russia',
'Cherokee': 'United Stated',
'Cheyenne': '',
'Chhattisgarhi': '',
'Chinese': 'China',
'Cornish': '',
'Corsican': 'France',
'Cree': 'Canada',
'Creek': '',
'Creole': '',
'Creoles and pidgins': '',
'Croatian': 'Croatia',
'Crow': '',
'Czech': 'Czech Republic',
'Danish': 'Denmark',
'Dari': 'Afghanistan',
'Desiya': '',
'Dinka': '',
'Djerma': '',
'Dogri': '',
'Dutch': 'Netherlands',
'Dyula': '',
'Dzongkha': '',
'East-Greenlandic': 'Greenland',
'Eastern Frisian': 'Germany',
'Egyptian (Ancient)': 'Egypt',
'English': 'United Kingdom',
'Esperanto': '',
'Estonian': 'Estonia',
'Ewe': '',
'Faliasch': '',
'Faroese': 'Faroe Islands',
'Filipino': 'Philippines',
'Finnish': 'Finland',
'Flemish': 'Belgium',
'Fon': '',
'French': 'France',
'Fulah': '',
'Fur': '',
'Gaelic': 'Ireland',
'Galician': '',
'Georgian': 'Georgia',
'German': 'Germany',
'Grebo': '',
'Greek': 'Greece',
'Greek, Ancient (to 1453)': 'Greece',
'Greenlandic': 'Greenland',
'Guarani': 'Paraguay',
'Gujarati': 'India',
'Gumatj': '',
'Gunwinggu': '',
'Haitian': 'Haiti',
'Hakka': 'China',
'Haryanvi': '',
'Hassanya': '',
'Hausa': '',
'Hawaiian': 'United States',
'Hebrew': 'Israel',
'Hindi': 'India',
'Hmong': '',
'Hokkien': '',
'Hopi': 'United States',
'Hungarian': 'Hungary',
'Iban': '',
'Ibo': 'Nigeria',
'Icelandic': 'Iceland',
'Indian': 'India',
'Indonesian': 'Indonesia',
'Inuktitut': '',
'Inupiaq': '',
'Irish Gaelic': 'Ireland',
'Italian': 'Italy',
'Japanese': 'Japan',
'Jola-Fonyi': '',
'Ju\'hoan': '',
'Kaado': '',
'Kabuverdianu': 'Cape Verde',
'Kabyle': '',
'Kalmyk-Oirat': '',
'Kannada': 'India',
'Karajá': '',
'Karbi': '',
'Karen': '',
'Kazakh': 'Kazakhstan',
'Khanty': 'Russia',
'Khasi': '',
'Kikuyu': '',
'Kinyarwanda': '',
'Kirundi': '',
'Klingon': '',
'Kodava': '',
'Konkani': 'India',
'Korean': 'South Korea',
'Korowai': 'Papua New Guinea',
'Kriolu': '',
'Kru': '',
'Kudmali': '',
'Kuna': '',
'Kurdish': 'Turkey', # ? one of multiple
'Kwakiutl': '',
'Kyrgyz': 'Kyrgyzstan',
'Ladakhi': '',
'Ladino': '',
'Lao': 'Laos',
'Latin': 'Italy',
'Latvian': 'Latvia',
'Limbu': '',
'Lingala': '',
'Lithuanian': 'Lithuania',
'Low German': 'Germany',
'Luxembourgish': 'Luxemburg',
'Macedonian': 'Macedonia',
'Macro-Jê': '',
'Magahi': '',
'Maithili': '',
'Malagasy': 'Madagascar',
'Malay': 'Malaysia',
'Malayalam': '',
'Malecite-Passamaquoddy': '',
'Malinka': '',
'Maltese': 'Malta',
'Manchu': '',
'Mandarin': 'China',
'Mandingo': '',
'Manipuri': '',
'Maori': 'New Zealand',
'Mapudungun': 'Chile',
'Marathi': 'India',
'Marshallese': 'Marshall Islands',
'Masai': '',
'Masalit': '',
'Maya': 'Mexico',
'Mende': 'Sierra Leone',
'Micmac': '',
'Middle English': 'England',
'Min Nan': '',
'Minangkabau': '',
'Mirandese': '',
'Mizo': '',
'Mohawk': '',
'Mongolian': 'Mongolia',
'Montagnais': '',
'More': 'Burkina Faso',
'Morisyen': '',
'Nagpuri': '',
'Nahuatl': '',
'Nama': '',
'Navajo': '',
'Naxi': 'China',
'Ndebele': '',
'Neapolitan': 'Italy',
'Nenets': '',
'Nepali': 'Nepal',
'Nisga\'a': '',
'None': '',
'Norse, Old': '',
'North American Indian': '',
'Norwegian': 'Norway',
'Nushi': '',
'Nyaneka': '',
'Nyanja': 'Malawi',
'Occitan': '',
'Ojibwa': '',
'Ojihimba': '',
'Old English': 'England',
'Oriya': '',
'Papiamento': '',
'Parsee': 'Iran',
'Pashtu': 'Afghanistan',
'Pawnee': '',
'Persian': 'Iran',
'Peul': '',
'Polish': 'Poland',
'Polynesian': '',
'Portuguese': 'Portugal',
'Pular': '',
'Punjabi': 'India',
'Purepecha': '',
'Quechua': 'Peru',
'Quenya': '',
'Rajasthani': 'India',
'Rawan': '',
'Romanian': 'Romania',
'Romansh': 'Switzerland',
'Romany': 'Romania',
'Rotuman': '',
'Russian': 'Russia',
'Ryukyuan': 'Japan',
'Saami': 'Finland',
'Samoan': 'Samoa',
'Sanskrit': '',
'Sardinian': 'Italy',
'Scanian': '',
'Serbian': 'Serbia',
'Serbo-Croatian': 'Yugoslavia',
'Serer': '',
'Shanghainese': 'China',
'Shanxi': '',
'Shona': 'Zimbabwe',
'Shoshoni': '',
'Sicilian': 'Italy',
'Sindarin': '',
'Sindhi': '',
'Sinhala': 'Sri Lanka',
'Sioux': '',
'Slovak': 'Slovakia',
'Slovenian': 'Slovenia',
'Somali': 'Somalia',
'Songhay': '',
'Soninke': '',
'Sorbian': 'Germany',
'Sotho': '',
'Sousson': '',
'Spanish': 'Spain',
'Sranan': '',
'Swahili': '',
'Swedish': 'Sweden',
'Swiss German': 'Switzerland',
'Sylheti': '',
'Tagalog': 'Philippines',
'Tajik': 'Tajikistan',
'Tamashek': '',
'Tamil': 'Sri Lanka',
'Tarahumara': '',
'Tatar': 'Russia',
'Telugu': 'India',
'Teochew': '',
'Thai': 'Thailand',
'Tibetan': 'China',
'Tigrigna': '',
'Tlingit': '',
'Tok Pisin': '',
'Tonga (Tonga Islands)': 'Tonga',
'Tsonga': '',
'Tswa': '',
'Tswana': '',
'Tulu': '',
'Tupi': '',
'Turkish': 'Turkey',
'Turkmen': 'Turkmenistan',
'Tuvinian': '',
'Tzotzil': '',
'Ukrainian': 'Ukraine',
'Ungwatsi': '',
'Urdu': 'Pakistan',
'Uzbek': 'Uzbekistan',
'Vietnamese': 'Vietnam',
'Visayan': '',
'Washoe': '',
'Welsh': 'Wales',
'Wolof': 'Senegal', # ? one of multiple
'Xhosa': 'South Africa',
'Yakut': '',
'Yapese': '',
'Yiddish': 'Israel',
'Yoruba': '',
'Zulu': 'South Africa'
},
'other': ['European Union', 'Metropolitan France', 'UK'],
'wikipedia_name': {
# ambiguous on wikipedia
@ -751,6 +1070,11 @@ def get_countries():
break
get_country_flag(country['code'], country['flagURL'])
get_country_icon(country['code'])
# languages
country['languages'] = []
for language, language_country in geo['languages'].iteritems():
if language_country == country['name']:
country['languages'].append(language)
write_json('../json/countries.json', countries)
return countries
@ -774,7 +1098,7 @@ def get_country_flag(code, url):
write_image(file, png)
for width in [256, 32]:
file = '../png/flags/' + str(width) + '/' + code + '.png'
if not os.path.exists(file):
if not os.path.exists(file) or True:
png_ = png.resize((width, int(round(width / png.size[0] * png.size[1]))), Image.ANTIALIAS)
write_image(file, png_)
@ -911,7 +1235,7 @@ def get_country_icon(code):
icon.paste(crop_right, (width, 0))
return icon
file = '../png/icons/1024/' + code + '.png'
if not os.path.exists(file):
if not os.path.exists(file) or True:
flag = Image.open('../png/flags/2048/' + code + '.png')
icon = None
functions = geo['icon'][code].split(' # ')[0].split('; ')
@ -950,7 +1274,7 @@ def get_country_icon(code):
icon = Image.open(file)
for width in [256, 16]:
file = '../png/icons/' + str(width) + '/' + code + '.png'
if not os.path.exists(file):
if not os.path.exists(file) or True:
write_image(file, icon.resize((width, width), Image.ANTIALIAS))
size = 256
mask_ = Image.open('../png/circle.png')
@ -961,7 +1285,9 @@ def get_country_icon(code):
icon_ = icon.resize((size, size), Image.ANTIALIAS)
mask_ = mask.resize((size, size), Image.ANTIALIAS)
marker.paste(icon_, (0, 0), mask_)
write_image('../png/markers/' + str(size) + '/' + code + '.png', marker)
file = '../png/markers/' + str(size) + '/' + code + '.png'
if not os.path.exists(file) or True:
write_image(file, marker)
def get_oxjs_languages():
# geonames_countries = get_geonames_countries()
@ -1127,6 +1453,10 @@ import wikipedia
if __name__ == '__main__':
write_json('../json/geo.json', geo)
countries = get_countries()
sys.exit()
file = '../txt/geonames.org/cities1000.txt'
geo['keys'] = read_json('../json/oxjs.org/geonames.keys.json')
keys = geo['keys']['place']['geonames.org']
@ -1139,10 +1469,6 @@ if __name__ == '__main__':
print len(data)
sys.exit()
write_json('../json/geo.json', geo)
countries = get_countries()
sys.exit()
cities = get_cities()
print cities, len(cities)