weather.py

   1 """Contains various object definitions needed by the weather utility."""
   2
   3 weather_copyright = """\
   4 # Copyright (c) 2006-2024 Jeremy Stanley <fungi@yuggoth.org>. Permission to
   5 # use, copy, modify, and distribute this software is granted under terms
   6 # provided in the LICENSE file distributed with this software.
   7 #"""
   8
   9 weather_version = "2.4.4"
  10
  11 radian_to_km = 6372.795484
  12 radian_to_mi = 3959.871528
  13
  14 def pyversion(ref=None):
  15     """Determine the Python version and optionally compare to a reference."""
  16     import platform
  17     ver = platform.python_version()
  18     if ref:
  19         return [
  20             int(x) for x in ver.split(".")[:2]
  21         ] >= [
  22             int(x) for x in ref.split(".")[:2]
  23         ]
  24     else: return ver
  25
  26 class Selections:
  27     """An object to contain selection data."""
  28     def __init__(self):
  29         """Store the config, options and arguments."""
  30         self.config = get_config()
  31         self.options, self.arguments = get_options(self.config)
  32         if self.get_bool("cache") and self.get_bool("cache_search") \
  33             and not self.get_bool("longlist"):
  34             integrate_search_cache(
  35                 self.config,
  36                 self.get("cachedir"),
  37                 self.get("setpath")
  38             )
  39         if not self.arguments:
  40             if "id" in self.options.__dict__ \
  41                 and self.options.__dict__["id"]:
  42                 self.arguments.append( self.options.__dict__["id"] )
  43                 del( self.options.__dict__["id"] )
  44                 import sys
  45                 message = "WARNING: the --id option is deprecated and will eventually be removed\n"
  46                 sys.stderr.write(message)
  47             elif "city" in self.options.__dict__ \
  48                 and self.options.__dict__["city"] \
  49                 and "st" in self.options.__dict__ \
  50                 and self.options.__dict__["st"]:
  51                 self.arguments.append(
  52                     "^%s city, %s" % (
  53                         self.options.__dict__["city"],
  54                         self.options.__dict__["st"]
  55                     )
  56                 )
  57                 del( self.options.__dict__["city"] )
  58                 del( self.options.__dict__["st"] )
  59                 import sys
  60                 message = "WARNING: the --city/--st options are deprecated and will eventually be removed\n"
  61                 sys.stderr.write(message)
  62     def get(self, option, argument=None):
  63         """Retrieve data from the config or options."""
  64         if argument:
  65             if self.config.has_section(argument) and (
  66                 self.config.has_option(argument, "city") \
  67                     or self.config.has_option(argument, "id") \
  68                     or self.config.has_option(argument, "st")
  69             ):
  70                 self.config.remove_section(argument)
  71                 import sys
  72                 message = "WARNING: the city/id/st options are now unsupported in aliases\n"
  73                 sys.stderr.write(message)
  74             if not self.config.has_section(argument):
  75                 guessed = guess(
  76                     argument,
  77                     path=self.get("setpath"),
  78                     info=self.get("info"),
  79                     cache_search=(
  80                         self.get("cache") and self.get("cache_search")
  81                     ),
  82                     cachedir=self.get("cachedir"),
  83                     quiet=self.get_bool("quiet")
  84                 )
  85                 self.config.add_section(argument)
  86                 for item in guessed.items():
  87                     self.config.set(argument, *item)
  88             if self.config.has_option(argument, option):
  89                 return self.config.get(argument, option)
  90         if option in self.options.__dict__:
  91             return self.options.__dict__[option]
  92         import sys
  93         message = "WARNING: no URI defined for %s\n" % option
  94         sys.stderr.write(message)
  95         return None
  96     def get_bool(self, option, argument=None):
  97         """Get data and coerce to a boolean if necessary."""
  98         # Mimic configparser's getboolean() method by treating
  99         # false/no/off/0 as False and true/yes/on/1 as True values,
 100         # case-insensitively
 101         value = self.get(option, argument)
 102         if isinstance(value, bool):
 103             return value
 104         if isinstance(value, str):
 105             vlower = value.lower()
 106             if vlower in ('false', 'no', 'off', '0'):
 107                 return False
 108             elif vlower in ('true', 'yes', 'on', '1'):
 109                 return True
 110         raise ValueError("Not a boolean: %s" % value)
 111     def getint(self, option, argument=None):
 112         """Get data and coerce to an integer if necessary."""
 113         value = self.get(option, argument)
 114         if value: return int(value)
 115         else: return 0
 116
 117 def average(coords):
 118     """Average a list of coordinates."""
 119     x = 0
 120     y = 0
 121     for coord in coords:
 122         x += coord[0]
 123         y += coord[1]
 124     count = len(coords)
 125     return (x/count, y/count)
 126
 127 def filter_units(line, units="imperial"):
 128     """Filter or convert units in a line of text between US/UK and metric."""
 129     import re
 130     # filter lines with both pressures in the form of "X inches (Y hPa)" or
 131     # "X in. Hg (Y hPa)"
 132     dual_p = re.match(
 133         r"(.* )(\d*(\.\d+)? (inches|in\. Hg)) \((\d*(\.\d+)? hPa)\)(.*)",
 134         line
 135     )
 136     if dual_p:
 137         preamble, in_hg, i_fr, i_un, hpa, h_fr, trailer = dual_p.groups()
 138         if units == "imperial": line = preamble + in_hg + trailer
 139         elif units == "metric": line = preamble + hpa + trailer
 140     # filter lines with both temperatures in the form of "X F (Y C)"
 141     dual_t = re.match(
 142         r"(.* )(-?\d*(\.\d+)? F) \((-?\d*(\.\d+)? C)\)(.*)",
 143         line
 144     )
 145     if dual_t:
 146         preamble, fahrenheit, f_fr, celsius, c_fr, trailer = dual_t.groups()
 147         if units == "imperial": line = preamble + fahrenheit + trailer
 148         elif units == "metric": line = preamble + celsius + trailer
 149     # if metric is desired, convert distances in the form of "X mile(s)" to
 150     # "Y kilometer(s)"
 151     if units == "metric":
 152         imperial_d = re.match(
 153             r"(.* )(\d+)( mile\(s\))(.*)",
 154             line
 155         )
 156         if imperial_d:
 157             preamble, mi, m_u, trailer = imperial_d.groups()
 158             line = preamble + str(int(round(int(mi)*1.609344))) \
 159                 + " kilometer(s)" + trailer
 160     # filter speeds in the form of "X MPH (Y KT)" to just "X MPH"; if metric is
 161     # desired, convert to "Z KPH"
 162     imperial_s = re.match(
 163         r"(.* )(\d+)( MPH)( \(\d+ KT\))(.*)",
 164         line
 165     )
 166     if imperial_s:
 167         preamble, mph, m_u, kt, trailer = imperial_s.groups()
 168         if units == "imperial": line = preamble + mph + m_u + trailer
 169         elif units == "metric":
 170             line = preamble + str(int(round(int(mph)*1.609344))) + " KPH" + \
 171                 trailer
 172     imperial_s = re.match(
 173         r"(.* )(\d+)( MPH)( \(\d+ KT\))(.*)",
 174         line
 175     )
 176     if imperial_s:
 177         preamble, mph, m_u, kt, trailer = imperial_s.groups()
 178         if units == "imperial": line = preamble + mph + m_u + trailer
 179         elif units == "metric":
 180             line = preamble + str(int(round(int(mph)*1.609344))) + " KPH" + \
 181                 trailer
 182     # if imperial is desired, qualify given forcast temperatures like "X F"; if
 183     # metric is desired, convert to "Y C"
 184     imperial_t = re.match(
 185         r"(.* )(High |high |Low |low )(\d+)(\.|,)(.*)",
 186         line
 187     )
 188     if imperial_t:
 189         preamble, parameter, fahrenheit, sep, trailer = imperial_t.groups()
 190         if units == "imperial":
 191             line = preamble + parameter + fahrenheit + " F" + sep + trailer
 192         elif units == "metric":
 193             line = preamble + parameter \
 194                 + str(int(round((int(fahrenheit)-32)*5/9))) + " C" + sep \
 195                 + trailer
 196     # hand off the resulting line
 197     return line
 198
 199 def get_uri(
 200     uri,
 201     ignore_fail=False,
 202     cache_data=False,
 203     cacheage=900,
 204     cachedir="."
 205 ):
 206     """Return a string containing the results of a URI GET."""
 207     if pyversion("3"):
 208         import urllib, urllib.error, urllib.request
 209         URLError = urllib.error.URLError
 210         urlopen = urllib.request.urlopen
 211     else:
 212         import urllib2 as urllib
 213         URLError = urllib.URLError
 214         urlopen = urllib.urlopen
 215     import os, time
 216     if cache_data:
 217         dcachedir = os.path.join( os.path.expanduser(cachedir), "datacache" )
 218         if not os.path.exists(dcachedir):
 219             try: os.makedirs(dcachedir)
 220             except (IOError, OSError): pass
 221         dcache_fn = os.path.join(
 222             dcachedir,
 223             uri.split(":",1)[1].replace("/","_")
 224         )
 225     now = time.time()
 226     if cache_data and os.access(dcache_fn, os.R_OK) \
 227         and now-cacheage < os.stat(dcache_fn).st_mtime <= now:
 228         dcache_fd = open(dcache_fn)
 229         data = dcache_fd.read()
 230         dcache_fd.close()
 231     else:
 232         try:
 233             data = urlopen(uri).read().decode("utf-8")
 234         except URLError:
 235             if ignore_fail: return ""
 236             import os, sys
 237             sys.stderr.write("%s error: failed to retrieve\n   %s\n\n" % (
 238                 os.path.basename( sys.argv[0] ), uri))
 239             raise
 240         # Some data sources are HTML with the plain text wrapped in pre tags
 241         if "<pre>" in data:
 242             data = data[data.find("<pre>")+5:data.find("</pre>")]
 243         if cache_data:
 244             try:
 245                 import codecs
 246                 dcache_fd = codecs.open(dcache_fn, "w", "utf-8")
 247                 dcache_fd.write(data)
 248                 dcache_fd.close()
 249             except (IOError, OSError): pass
 250     return data
 251
 252 def get_metar(
 253     uri=None,
 254     verbose=False,
 255     quiet=False,
 256     headers=None,
 257     imperial=False,
 258     metric=False,
 259     cache_data=False,
 260     cacheage=900,
 261     cachedir="."
 262 ):
 263     """Return a summarized METAR for the specified station."""
 264     if not uri:
 265         import os, sys
 266         message = "%s error: METAR URI required for conditions\n" % \
 267             os.path.basename( sys.argv[0] )
 268         sys.stderr.write(message)
 269         sys.exit(1)
 270     metar = get_uri(
 271         uri,
 272         cache_data=cache_data,
 273         cacheage=cacheage,
 274         cachedir=cachedir
 275     )
 276     if pyversion("3") and type(metar) is bytes: metar = metar.decode("utf-8")
 277     if verbose: return metar
 278     else:
 279         import re
 280         lines = metar.split("\n")
 281         if not headers:
 282             headers = \
 283                 "relative_humidity," \
 284                 + "precipitation_last_hour," \
 285                 + "sky conditions," \
 286                 + "temperature," \
 287                 + "heat index," \
 288                 + "windchill," \
 289                 + "weather," \
 290                 + "wind"
 291         headerlist = headers.lower().replace("_"," ").split(",")
 292         output = []
 293         if not quiet:
 294             title = "Current conditions at %s"
 295             place = lines[0].split(", ")
 296             if len(place) > 1:
 297                 place = "%s, %s" % ( place[0].title(), place[1] )
 298             else: place = "<UNKNOWN>"
 299             output.append(title%place)
 300             output.append("Last updated " + lines[1])
 301         header_match = False
 302         for header in headerlist:
 303             for line in lines:
 304                 if line.lower().startswith(header + ":"):
 305                     if re.match(r".*:\d+$", line): line = line[:line.rfind(":")]
 306                     if imperial: line = filter_units(line, units="imperial")
 307                     elif metric: line = filter_units(line, units="metric")
 308                     if quiet: output.append(line)
 309                     else: output.append("   " + line)
 310                     header_match = True
 311         if not header_match:
 312             output.append(
 313                 "(no conditions matched your header list, try with --verbose)"
 314             )
 315         return "\n".join(output)
 316
 317 def get_alert(
 318     uri=None,
 319     verbose=False,
 320     quiet=False,
 321     cache_data=False,
 322     cacheage=900,
 323     cachedir="."
 324 ):
 325     """Return alert notice for the specified URI."""
 326     if not uri:
 327         return ""
 328     alert = get_uri(
 329         uri,
 330         ignore_fail=True,
 331         cache_data=cache_data,
 332         cacheage=cacheage,
 333         cachedir=cachedir
 334     ).strip()
 335     if pyversion("3") and type(alert) is bytes: alert = alert.decode("utf-8")
 336     if alert:
 337         if verbose: return alert
 338         else:
 339             import re
 340             if re.search(r"\nNational Weather Service", alert):
 341                 muted = True
 342             else:
 343                 muted = False
 344             lines = alert.split("\n")
 345             import time
 346             # TODO: make this offset configurable
 347             # TODO: adjust offset relative to the difference between the user's
 348             #       local time and the zone's local time (will need to extend
 349             #       the schema in the zones file to store each tz
 350             offset = 86400  # one day
 351
 352             # report alerts and forecasts that expired less than offset ago;
 353             # this is a cheap hack since expiration times seem to be relative
 354             # to the zone's local time zone, and converting from the user's
 355             # would get complicated, but also there can sometimes be a lag
 356             # between expiration and the next update
 357             valid_time = time.strftime(
 358                 "%Y%m%d%H%M", time.localtime(time.time() - offset))
 359             output = []
 360             for line in lines:
 361                 if line.startswith("Expires:") \
 362                     and "Expires:" + valid_time > line:
 363                     return ""
 364                 if muted and line.startswith("National Weather Service"):
 365                     muted = False
 366                     line = ""
 367                 elif line == "&&":
 368                     line = ""
 369                 elif line == "$$":
 370                     muted = True
 371                 if line and not muted:
 372                     if quiet: output.append(line)
 373                     else: output.append("   " + line)
 374             return "\n".join(output)
 375
 376 def get_options(config):
 377     """Parse the options passed on the command line."""
 378
 379     # for optparse's builtin -h/--help option
 380     usage = \
 381         "usage: %prog [options] [alias1|search1 [alias2|search2 [...]]]"
 382
 383     # for optparse's builtin --version option
 384     verstring = "%prog " + weather_version
 385
 386     # create the parser
 387     import optparse
 388     option_parser = optparse.OptionParser(usage=usage, version=verstring)
 389     # separate options object from list of arguments and return both
 390
 391     # the -a/--alert option
 392     if config.has_option("default", "alert"):
 393         default_alert = config.getboolean("default", "alert")
 394     else: default_alert = False
 395     option_parser.add_option("-a", "--alert",
 396         dest="alert",
 397         action="store_true",
 398         default=default_alert,
 399         help="include local alert notices")
 400
 401     # the --atypes option
 402     if config.has_option("default", "atypes"):
 403         default_atypes = config.get("default", "atypes")
 404     else:
 405         default_atypes = \
 406             "coastal_flood_statement," \
 407             + "flash_flood_statement," \
 408             + "flash_flood_warning," \
 409             + "flash_flood_watch," \
 410             + "flood_warning," \
 411             + "severe_thunderstorm_warning," \
 412             + "severe_weather_statement," \
 413             + "special_weather_statement," \
 414             + "tornado," \
 415             + "urgent_weather_message"
 416     option_parser.add_option("--atypes",
 417         dest="atypes",
 418         default=default_atypes,
 419         help="list of alert notification types to display")
 420
 421     # the --build-sets option
 422     option_parser.add_option("--build-sets",
 423         dest="build_sets",
 424         action="store_true",
 425         default=False,
 426         help="(re)build location correlation sets")
 427
 428     # the --cacheage option
 429     if config.has_option("default", "cacheage"):
 430         default_cacheage = config.getint("default", "cacheage")
 431     else: default_cacheage = 900
 432     option_parser.add_option("--cacheage",
 433         dest="cacheage",
 434         default=default_cacheage,
 435         help="duration in seconds to refresh cached data")
 436
 437     # the --cachedir option
 438     if config.has_option("default", "cachedir"):
 439         default_cachedir = config.get("default", "cachedir")
 440     else: default_cachedir = "~/.weather"
 441     option_parser.add_option("--cachedir",
 442         dest="cachedir",
 443         default=default_cachedir,
 444         help="directory for storing cached searches and data")
 445
 446     # the -f/--forecast option
 447     if config.has_option("default", "forecast"):
 448         default_forecast = config.getboolean("default", "forecast")
 449     else: default_forecast = False
 450     option_parser.add_option("-f", "--forecast",
 451         dest="forecast",
 452         action="store_true",
 453         default=default_forecast,
 454         help="include a local forecast")
 455
 456     # the --headers option
 457     if config.has_option("default", "headers"):
 458         default_headers = config.get("default", "headers")
 459     else:
 460         default_headers = \
 461             "temperature," \
 462             + "relative_humidity," \
 463             + "wind," \
 464             + "heat_index," \
 465             + "windchill," \
 466             + "weather," \
 467             + "sky_conditions," \
 468             + "precipitation_last_hour"
 469     option_parser.add_option("--headers",
 470         dest="headers",
 471         default=default_headers,
 472         help="list of conditions headers to display")
 473
 474     # the --imperial option
 475     if config.has_option("default", "imperial"):
 476         default_imperial = config.getboolean("default", "imperial")
 477     else: default_imperial = False
 478     option_parser.add_option("--imperial",
 479         dest="imperial",
 480         action="store_true",
 481         default=default_imperial,
 482         help="filter/convert conditions for US/UK units")
 483
 484     # the --info option
 485     option_parser.add_option("--info",
 486         dest="info",
 487         action="store_true",
 488         default=False,
 489         help="output detailed information for your search")
 490
 491     # the -l/--list option
 492     option_parser.add_option("-l", "--list",
 493         dest="list",
 494         action="store_true",
 495         default=False,
 496         help="list all configured aliases and cached searches")
 497
 498     # the --longlist option
 499     option_parser.add_option("--longlist",
 500         dest="longlist",
 501         action="store_true",
 502         default=False,
 503         help="display details of all configured aliases")
 504
 505     # the -m/--metric option
 506     if config.has_option("default", "metric"):
 507         default_metric = config.getboolean("default", "metric")
 508     else: default_metric = False
 509     option_parser.add_option("-m", "--metric",
 510         dest="metric",
 511         action="store_true",
 512         default=default_metric,
 513         help="filter/convert conditions for metric units")
 514
 515     # the -n/--no-conditions option
 516     if config.has_option("default", "conditions"):
 517         default_conditions = config.getboolean("default", "conditions")
 518     else: default_conditions = True
 519     option_parser.add_option("-n", "--no-conditions",
 520         dest="conditions",
 521         action="store_false",
 522         default=default_conditions,
 523         help="disable output of current conditions")
 524
 525     # the --no-cache option
 526     if config.has_option("default", "cache"):
 527         default_cache = config.getboolean("default", "cache")
 528     else: default_cache = True
 529     option_parser.add_option("--no-cache",
 530         dest="cache",
 531         action="store_false",
 532         default=True,
 533         help="disable all caching (searches and data)")
 534
 535     # the --no-cache-data option
 536     if config.has_option("default", "cache_data"):
 537         default_cache_data = config.getboolean("default", "cache_data")
 538     else: default_cache_data = True
 539     option_parser.add_option("--no-cache-data",
 540         dest="cache_data",
 541         action="store_false",
 542         default=True,
 543         help="disable retrieved data caching")
 544
 545     # the --no-cache-search option
 546     if config.has_option("default", "cache_search"):
 547         default_cache_search = config.getboolean("default", "cache_search")
 548     else: default_cache_search = True
 549     option_parser.add_option("--no-cache-search",
 550         dest="cache_search",
 551         action="store_false",
 552         default=True,
 553         help="disable search result caching")
 554
 555     # the -q/--quiet option
 556     if config.has_option("default", "quiet"):
 557         default_quiet = config.getboolean("default", "quiet")
 558     else: default_quiet = False
 559     option_parser.add_option("-q", "--quiet",
 560         dest="quiet",
 561         action="store_true",
 562         default=default_quiet,
 563         help="skip preambles and don't indent")
 564
 565     # the --setpath option
 566     if config.has_option("default", "setpath"):
 567         default_setpath = config.get("default", "setpath")
 568     else: default_setpath = ".:~/.weather"
 569     option_parser.add_option("--setpath",
 570         dest="setpath",
 571         default=default_setpath,
 572         help="directory search path for correlation sets")
 573
 574     # the -v/--verbose option
 575     if config.has_option("default", "verbose"):
 576         default_verbose = config.getboolean("default", "verbose")
 577     else: default_verbose = False
 578     option_parser.add_option("-v", "--verbose",
 579         dest="verbose",
 580         action="store_true",
 581         default=default_verbose,
 582         help="show full decoded feeds")
 583
 584     # deprecated options
 585     if config.has_option("default", "city"):
 586         default_city = config.get("default", "city")
 587     else: default_city = ""
 588     option_parser.add_option("-c", "--city",
 589         dest="city",
 590         default=default_city,
 591         help=optparse.SUPPRESS_HELP)
 592     if config.has_option("default", "id"):
 593         default_id = config.get("default", "id")
 594     else: default_id = ""
 595     option_parser.add_option("-i", "--id",
 596         dest="id",
 597         default=default_id,
 598         help=optparse.SUPPRESS_HELP)
 599     if config.has_option("default", "st"):
 600         default_st = config.get("default", "st")
 601     else: default_st = ""
 602     option_parser.add_option("-s", "--st",
 603         dest="st",
 604         default=default_st,
 605         help=optparse.SUPPRESS_HELP)
 606
 607     options, arguments = option_parser.parse_args()
 608     return options, arguments
 609
 610 def get_config():
 611     """Parse the aliases and configuration."""
 612     if pyversion("3"): import configparser
 613     else: import ConfigParser as configparser
 614     config = configparser.ConfigParser()
 615     import os
 616     rcfiles = [
 617         "/etc/weatherrc",
 618         "/etc/weather/weatherrc",
 619         os.path.expanduser("~/.weather/weatherrc"),
 620         os.path.expanduser("~/.weatherrc"),
 621         "weatherrc"
 622         ]
 623     for rcfile in rcfiles:
 624         if os.access(rcfile, os.R_OK):
 625             if pyversion("3"):
 626                 config.read(rcfile, encoding="utf-8")
 627             else:
 628                 config.read(rcfile)
 629     for section in config.sections():
 630         if section != section.lower():
 631             if config.has_section(section.lower()):
 632                 config.remove_section(section.lower())
 633             config.add_section(section.lower())
 634             for option,value in config.items(section):
 635                 config.set(section.lower(), option, value)
 636     return config
 637
 638 def integrate_search_cache(config, cachedir, setpath):
 639     """Add cached search results into the configuration."""
 640     if pyversion("3"): import configparser
 641     else: import ConfigParser as configparser
 642     import os, time
 643     scache_fn = os.path.join( os.path.expanduser(cachedir), "searches" )
 644     if not os.access(scache_fn, os.R_OK): return config
 645     scache_fd = open(scache_fn)
 646     created = float( scache_fd.readline().split(":")[1].strip().split()[0] )
 647     scache_fd.close()
 648     now = time.time()
 649     datafiles = data_index(setpath)
 650     if datafiles:
 651         data_freshness = sorted(
 652             [ x[1] for x in datafiles.values() ],
 653             reverse=True
 654         )[0]
 655     else: data_freshness = now
 656     if created < data_freshness <= now:
 657         try:
 658             os.remove(scache_fn)
 659             print( "[clearing outdated %s]" % scache_fn )
 660         except (IOError, OSError):
 661             pass
 662         return config
 663     scache = configparser.ConfigParser()
 664     if pyversion("3"):
 665         scache.read(scache_fn, encoding="utf-8")
 666     else:
 667         scache.read(scache_fn)
 668     for section in scache.sections():
 669         if not config.has_section(section):
 670             config.add_section(section)
 671             for option,value in scache.items(section):
 672                 config.set(section, option, value)
 673     return config
 674
 675 def list_aliases(config, detail=False):
 676     """Return a formatted list of aliases defined in the config."""
 677     if detail:
 678         output = "\n# configured alias details..."
 679         for section in sorted(config.sections()):
 680             output += "\n\n[%s]" % section
 681             for item in sorted(config.items(section)):
 682                 output += "\n%s = %s" % item
 683         output += "\n"
 684     else:
 685         output = "configured aliases and cached searches..."
 686         for section in sorted(config.sections()):
 687             if config.has_option(section, "description"):
 688                 description = config.get(section, "description")
 689             else: description = "(no description provided)"
 690             output += "\n   %s: %s" % (section, description)
 691     return output
 692
 693 def data_index(path):
 694     import os
 695     datafiles = {}
 696     for filename in ("airports", "places", "stations", "zctas", "zones"):
 697         for dirname in path.split(":"):
 698             for extension in ("", ".gz", ".txt"):
 699                 candidate = os.path.expanduser(
 700                     os.path.join( dirname, "".join( (filename, extension) ) )
 701                 )
 702                 if os.path.exists(candidate):
 703                     datafiles[filename] = (
 704                         candidate,
 705                         os.stat(candidate).st_mtime
 706                     )
 707                     break
 708             if filename in datafiles:
 709                 break
 710     return datafiles
 711
 712 def guess(
 713     expression,
 714     path=".",
 715     max_results=20,
 716     info=False,
 717     cache_search=False,
 718     cacheage=900,
 719     cachedir=".",
 720     quiet=False
 721 ):
 722     """Find URIs using airport, gecos, placename, station, ZCTA/ZIP, zone."""
 723     import codecs, datetime, time, os, re, sys
 724     if pyversion("3"): import configparser
 725     else: import ConfigParser as configparser
 726     datafiles = data_index(path)
 727     if re.match("[A-Za-z]{3}$", expression): searchtype = "airport"
 728     elif re.match("[A-Za-z0-9]{4}$", expression): searchtype = "station"
 729     elif re.match("[A-Za-z]{2}[Zz][0-9]{3}$", expression): searchtype = "zone"
 730     elif re.match("[0-9]{5}$", expression): searchtype = "ZCTA"
 731     elif re.match(
 732         r"[\+-]?\d+(\.\d+)?(-\d+){,2}[ENSWensw]?, *[\+-]?\d+(\.\d+)?(-\d+){,2}[ENSWensw]?$",
 733         expression
 734     ):
 735         searchtype = "coordinates"
 736     elif re.match(r"(FIPS|fips)\d+$", expression): searchtype = "FIPS"
 737     else:
 738         searchtype = "name"
 739         cache_search = False
 740     if cache_search: action = "caching"
 741     else: action = "using"
 742     if info:
 743         scores = [
 744             (0.005, "bad"),
 745             (0.025, "poor"),
 746             (0.160, "suspect"),
 747             (0.500, "mediocre"),
 748             (0.840, "good"),
 749             (0.975, "great"),
 750             (0.995, "excellent"),
 751             (1.000, "ideal"),
 752         ]
 753     if not quiet: print("Searching via %s..."%searchtype)
 754     stations = configparser.ConfigParser()
 755     dataname = "stations"
 756     if dataname in datafiles:
 757         datafile = datafiles[dataname][0]
 758         if datafile.endswith(".gz"):
 759             import gzip
 760             if pyversion("3"):
 761                 stations.read_string(
 762                     gzip.open(datafile).read().decode("utf-8") )
 763             else: stations.read_file( gzip.open(datafile) )
 764         else:
 765             if pyversion("3"):
 766                 stations.read(datafile, encoding="utf-8")
 767             else:
 768                 stations.read(datafile)
 769     else:
 770         message = "%s error: can't find \"%s\" data file\n" % (
 771             os.path.basename( sys.argv[0] ),
 772             dataname
 773         )
 774         sys.stderr.write(message)
 775         exit(1)
 776     zones = configparser.ConfigParser()
 777     dataname = "zones"
 778     if dataname in datafiles:
 779         datafile = datafiles[dataname][0]
 780         if datafile.endswith(".gz"):
 781             import gzip
 782             if pyversion("3"):
 783                 zones.read_string( gzip.open(datafile).read().decode("utf-8") )
 784             else: zones.read_file( gzip.open(datafile) )
 785         else:
 786             if pyversion("3"):
 787                 zones.read(datafile, encoding="utf-8")
 788             else:
 789                 zones.read(datafile)
 790     else:
 791         message = "%s error: can't find \"%s\" data file\n" % (
 792             os.path.basename( sys.argv[0] ),
 793             dataname
 794         )
 795         sys.stderr.write(message)
 796         exit(1)
 797     search = None
 798     station = ("", 0)
 799     zone = ("", 0)
 800     dataset = None
 801     possibilities = []
 802     uris = {}
 803     if searchtype == "airport":
 804         expression = expression.lower()
 805         airports = configparser.ConfigParser()
 806         dataname = "airports"
 807         if dataname in datafiles:
 808             datafile = datafiles[dataname][0]
 809             if datafile.endswith(".gz"):
 810                 import gzip
 811                 if pyversion("3"):
 812                     airports.read_string(
 813                         gzip.open(datafile).read().decode("utf-8") )
 814                 else: airports.read_file( gzip.open(datafile) )
 815             else:
 816                 if pyversion("3"):
 817                     airports.read(datafile, encoding="utf-8")
 818                 else:
 819                     airports.read(datafile)
 820         else:
 821             message = "%s error: can't find \"%s\" data file\n" % (
 822                 os.path.basename( sys.argv[0] ),
 823                 dataname
 824             )
 825             sys.stderr.write(message)
 826             exit(1)
 827         if airports.has_section(expression) \
 828             and airports.has_option(expression, "station"):
 829             search = (expression, "IATA/FAA airport code %s" % expression)
 830             station = ( airports.get(expression, "station"), 0 )
 831             if stations.has_option(station[0], "zone"):
 832                 zone = eval( stations.get(station[0], "zone") )
 833                 dataset = stations
 834             if not ( info or quiet ) \
 835                 and stations.has_option( station[0], "description" ):
 836                 print(
 837                     "[%s result %s]" % (
 838                         action,
 839                         stations.get(station[0], "description")
 840                     )
 841                 )
 842         else:
 843             message = "No IATA/FAA airport code \"%s\" in the %s file.\n" % (
 844                 expression,
 845                 datafiles["airports"][0]
 846             )
 847             sys.stderr.write(message)
 848             exit(1)
 849     elif searchtype == "station":
 850         expression = expression.lower()
 851         if stations.has_section(expression):
 852             station = (expression, 0)
 853             if not search:
 854                 search = (expression, "ICAO station code %s" % expression)
 855             if stations.has_option(expression, "zone"):
 856                 zone = eval( stations.get(expression, "zone") )
 857                 dataset = stations
 858             if not ( info or quiet ) \
 859                 and stations.has_option(expression, "description"):
 860                 print(
 861                     "[%s result %s]" % (
 862                         action,
 863                         stations.get(expression, "description")
 864                     )
 865                 )
 866         else:
 867             message = "No ICAO weather station \"%s\" in the %s file.\n" % (
 868                 expression,
 869                 datafiles["stations"][0]
 870             )
 871             sys.stderr.write(message)
 872             exit(1)
 873     elif searchtype == "zone":
 874         expression = expression.lower()
 875         if zones.has_section(expression) \
 876             and zones.has_option(expression, "station"):
 877             zone = (expression, 0)
 878             station = eval( zones.get(expression, "station") )
 879             dataset = zones
 880             search = (expression, "NWS/NOAA weather zone %s" % expression)
 881             if not ( info or quiet ) \
 882                 and zones.has_option(expression, "description"):
 883                 print(
 884                     "[%s result %s]" % (
 885                         action,
 886                         zones.get(expression, "description")
 887                     )
 888                 )
 889         else:
 890             message = "No usable NWS weather zone \"%s\" in the %s file.\n" % (
 891                 expression,
 892                 datafiles["zones"][0]
 893             )
 894             sys.stderr.write(message)
 895             exit(1)
 896     elif searchtype == "ZCTA":
 897         zctas = configparser.ConfigParser()
 898         dataname = "zctas"
 899         if dataname in datafiles:
 900             datafile = datafiles[dataname][0]
 901             if datafile.endswith(".gz"):
 902                 import gzip
 903                 if pyversion("3"):
 904                     zctas.read_string(
 905                         gzip.open(datafile).read().decode("utf-8") )
 906                 else: zctas.read_file( gzip.open(datafile) )
 907             else:
 908                 if pyversion("3"):
 909                     zctas.read(datafile, encoding="utf-8")
 910                 else:
 911                     zctas.read(datafile)
 912         else:
 913             message = "%s error: can't find \"%s\" data file\n" % (
 914                 os.path.basename( sys.argv[0] ),
 915                 dataname
 916             )
 917             sys.stderr.write(message)
 918             exit(1)
 919         dataset = zctas
 920         if zctas.has_section(expression) \
 921             and zctas.has_option(expression, "station"):
 922             station = eval( zctas.get(expression, "station") )
 923             search = (expression, "Census ZCTA (ZIP code) %s" % expression)
 924             if zctas.has_option(expression, "zone"):
 925                 zone = eval( zctas.get(expression, "zone") )
 926         else:
 927             message = "No census ZCTA (ZIP code) \"%s\" in the %s file.\n" % (
 928                 expression,
 929                 datafiles["zctas"][0]
 930             )
 931             sys.stderr.write(message)
 932             exit(1)
 933     elif searchtype == "coordinates":
 934         search = (expression, "Geographic coordinates %s" % expression)
 935         stationtable = {}
 936         for station in stations.sections():
 937             if stations.has_option(station, "location"):
 938                 stationtable[station] = {
 939                     "location": eval( stations.get(station, "location") )
 940                 }
 941         station = closest( gecos(expression), stationtable, "location", 0.1 )
 942         if not station[0]:
 943             message = "No ICAO weather station found near %s.\n" % expression
 944             sys.stderr.write(message)
 945             exit(1)
 946         zonetable = {}
 947         for zone in zones.sections():
 948             if zones.has_option(zone, "centroid"):
 949                 zonetable[zone] = {
 950                     "centroid": eval( zones.get(zone, "centroid") )
 951                 }
 952         zone = closest( gecos(expression), zonetable, "centroid", 0.1 )
 953         if not zone[0]:
 954             message = "No NWS weather zone near %s; forecasts unavailable.\n" \
 955                 % expression
 956             sys.stderr.write(message)
 957     elif searchtype in ("FIPS", "name"):
 958         places = configparser.ConfigParser()
 959         dataname = "places"
 960         if dataname in datafiles:
 961             datafile = datafiles[dataname][0]
 962             if datafile.endswith(".gz"):
 963                 import gzip
 964                 if pyversion("3"):
 965                     places.read_string(
 966                         gzip.open(datafile).read().decode("utf-8") )
 967                 else: places.read_file( gzip.open(datafile) )
 968             else:
 969                 if pyversion("3"):
 970                     places.read(datafile, encoding="utf-8")
 971                 else:
 972                     places.read(datafile)
 973         else:
 974             message = "%s error: can't find \"%s\" data file\n" % (
 975                 os.path.basename( sys.argv[0] ),
 976                 dataname
 977             )
 978             sys.stderr.write(message)
 979             exit(1)
 980         dataset = places
 981         place = expression.lower()
 982         if places.has_section(place) and places.has_option(place, "station"):
 983             station = eval( places.get(place, "station") )
 984             search = (expression, "Census Place %s" % expression)
 985             if places.has_option(place, "description"):
 986                 search = (
 987                     search[0],
 988                     search[1] + ", %s" % places.get(place, "description")
 989                 )
 990             if places.has_option(place, "zone"):
 991                 zone = eval( places.get(place, "zone") )
 992             if not ( info or quiet ) \
 993                 and places.has_option(place, "description"):
 994                 print(
 995                     "[%s result %s]" % (
 996                         action,
 997                         places.get(place, "description")
 998                     )
 999                 )
1000         else:
1001             for place in places.sections():
1002                 if places.has_option(place, "description") \
1003                     and places.has_option(place, "station") \
1004                     and re.search(
1005                         expression,
1006                         places.get(place, "description"),
1007                         re.I
1008                     ):
1009                         possibilities.append(place)
1010             for place in stations.sections():
1011                 if stations.has_option(place, "description") \
1012                     and re.search(
1013                         expression,
1014                         stations.get(place, "description"),
1015                         re.I
1016                     ):
1017                         possibilities.append(place)
1018             for place in zones.sections():
1019                 if zones.has_option(place, "description") \
1020                     and zones.has_option(place, "station") \
1021                     and re.search(
1022                         expression,
1023                         zones.get(place, "description"),
1024                         re.I
1025                     ):
1026                         possibilities.append(place)
1027             if len(possibilities) == 1:
1028                 place = possibilities[0]
1029                 if places.has_section(place):
1030                     station = eval( places.get(place, "station") )
1031                     description = places.get(place, "description")
1032                     if places.has_option(place, "zone"):
1033                         zone = eval( places.get(place, "zone" ) )
1034                     search = ( expression, "%s: %s" % (place, description) )
1035                 elif stations.has_section(place):
1036                     station = (place, 0.0)
1037                     description = stations.get(place, "description")
1038                     if stations.has_option(place, "zone"):
1039                         zone = eval( stations.get(place, "zone" ) )
1040                     search = ( expression, "ICAO station code %s" % place )
1041                 elif zones.has_section(place):
1042                     station = eval( zones.get(place, "station") )
1043                     description = zones.get(place, "description")
1044                     zone = (place, 0.0)
1045                     search = ( expression, "NWS/NOAA weather zone %s" % place )
1046                 if not ( info or quiet ):
1047                     print( "[%s result %s]" % (action, description) )
1048             if not possibilities and not station[0]:
1049                 message = "No FIPS code/census area match in the %s file.\n" % (
1050                     datafiles["places"][0]
1051                 )
1052                 sys.stderr.write(message)
1053                 exit(1)
1054     if station[0]:
1055         uris["metar"] = stations.get( station[0], "metar" )
1056         if zone[0]:
1057             for key,value in zones.items( zone[0] ):
1058                 if key not in ("centroid", "description", "station"):
1059                     uris[key] = value
1060     elif possibilities:
1061         count = len(possibilities)
1062         if count <= max_results:
1063             print( "Your search is ambiguous, returning %s matches:" % count )
1064             for place in sorted(possibilities):
1065                 if places.has_section(place):
1066                     print(
1067                         "   [%s] %s" % (
1068                             place,
1069                             places.get(place, "description")
1070                         )
1071                     )
1072                 elif stations.has_section(place):
1073                     print(
1074                         "   [%s] %s" % (
1075                             place,
1076                             stations.get(place, "description")
1077                         )
1078                     )
1079                 elif zones.has_section(place):
1080                     print(
1081                         "   [%s] %s" % (
1082                             place,
1083                             zones.get(place, "description")
1084                         )
1085                     )
1086         else:
1087             print(
1088                 "Your search is too ambiguous, returning %s matches." % count
1089             )
1090         exit(0)
1091     if info:
1092         stationlist = []
1093         zonelist = []
1094         if dataset:
1095             for section in dataset.sections():
1096                 if dataset.has_option(section, "station"):
1097                     stationlist.append(
1098                         eval( dataset.get(section, "station") )[1]
1099                     )
1100                 if dataset.has_option(section, "zone"):
1101                     zonelist.append( eval( dataset.get(section, "zone") )[1] )
1102         stationlist.sort()
1103         zonelist.sort()
1104         scount = len(stationlist)
1105         zcount = len(zonelist)
1106         sranks = []
1107         zranks = []
1108         for score in scores:
1109             if stationlist:
1110                 sranks.append( stationlist[ int( (1-score[0]) * scount ) ] )
1111             if zonelist:
1112                 zranks.append( zonelist[ int( (1-score[0]) * zcount ) ] )
1113         description = search[1]
1114         uris["description"] = description
1115         print(
1116             "%s\n%s" % ( description, "-" * len(description) )
1117         )
1118         print(
1119             "%s: %s" % (
1120                 station[0],
1121                 stations.get( station[0], "description" )
1122             )
1123         )
1124         km = radian_to_km*station[1]
1125         mi = radian_to_mi*station[1]
1126         if sranks and not description.startswith("ICAO station code "):
1127             for index in range(0, len(scores)):
1128                 if station[1] >= sranks[index]:
1129                     score = scores[index][1]
1130                     break
1131             print(
1132                 "   (proximity %s, %.3gkm, %.3gmi)" % ( score, km, mi )
1133             )
1134         elif searchtype == "coordinates":
1135             print( "   (%.3gkm, %.3gmi)" % (km, mi) )
1136         if zone[0]:
1137             print(
1138                 "%s: %s" % ( zone[0], zones.get( zone[0], "description" ) )
1139             )
1140         km = radian_to_km*zone[1]
1141         mi = radian_to_mi*zone[1]
1142         if zranks and not description.startswith("NWS/NOAA weather zone "):
1143             for index in range(0, len(scores)):
1144                 if zone[1] >= zranks[index]:
1145                     score = scores[index][1]
1146                     break
1147             print(
1148                 "   (proximity %s, %.3gkm, %.3gmi)" % ( score, km, mi )
1149             )
1150         elif searchtype == "coordinates" and zone[0]:
1151             print( "   (%.3gkm, %.3gmi)" % (km, mi) )
1152     if cache_search:
1153         now = time.time()
1154         nowstamp = "%s (%s)" % (
1155             now,
1156             datetime.datetime.isoformat(
1157                 datetime.datetime.fromtimestamp(now),
1158                 " "
1159             )
1160         )
1161         search_cache = ["\n"]
1162         search_cache.append( "[%s]\n" % search[0] )
1163         search_cache.append( "cached = %s\n" % nowstamp )
1164         for uriname in sorted(uris.keys()):
1165             search_cache.append( "%s = %s\n" % ( uriname, uris[uriname] ) )
1166         real_cachedir = os.path.expanduser(cachedir)
1167         if not os.path.exists(real_cachedir):
1168             try: os.makedirs(real_cachedir)
1169             except (IOError, OSError): pass
1170         scache_fn = os.path.join(real_cachedir, "searches")
1171         if not os.path.exists(scache_fn):
1172             then = sorted(
1173                     [ x[1] for x in datafiles.values() ],
1174                     reverse=True
1175                 )[0]
1176             thenstamp = "%s (%s)" % (
1177                 then,
1178                 datetime.datetime.isoformat(
1179                     datetime.datetime.fromtimestamp(then),
1180                     " "
1181                 )
1182             )
1183             search_cache.insert(
1184                 0,
1185                 "# based on data files from: %s\n" % thenstamp
1186             )
1187         try:
1188             scache_existing = configparser.ConfigParser()
1189             if pyversion("3"):
1190                 scache_existing.read(scache_fn, encoding="utf-8")
1191             else:
1192                 scache_existing.read(scache_fn)
1193             if not scache_existing.has_section(search[0]):
1194                 scache_fd = codecs.open(scache_fn, "a", "utf-8")
1195                 scache_fd.writelines(search_cache)
1196                 scache_fd.close()
1197         except (IOError, OSError): pass
1198     if not info:
1199         return(uris)
1200
1201 def closest(position, nodes, fieldname, angle=None):
1202     import math
1203     if not angle: angle = 2*math.pi
1204     match = None
1205     for name in nodes:
1206         if fieldname in nodes[name]:
1207             node = nodes[name][fieldname]
1208             if node and abs( position[0]-node[0] ) < angle:
1209                 if abs( position[1]-node[1] ) < angle \
1210                     or abs( abs( position[1]-node[1] ) - 2*math.pi ) < angle:
1211                     if position == node:
1212                         angle = 0
1213                         match = name
1214                     else:
1215                         candidate = math.acos(
1216                             math.sin( position[0] ) * math.sin( node[0] ) \
1217                                 + math.cos( position[0] ) \
1218                                 * math.cos( node[0] ) \
1219                                 * math.cos( position[1] - node[1] )
1220                             )
1221                         if candidate < angle:
1222                             angle = candidate
1223                             match = name
1224     if match: match = str(match)
1225     return (match, angle)
1226
1227 def gecos(formatted):
1228     import math, re
1229     coordinates = formatted.split(",")
1230     for coordinate in range(0, 2):
1231         degrees, foo, minutes, bar, seconds, hemisphere = re.match(
1232             r"([\+-]?\d+\.?\d*)(-(\d+))?(-(\d+))?([ensw]?)$",
1233             coordinates[coordinate].strip().lower()
1234         ).groups()
1235         value = float(degrees)
1236         if minutes: value += float(minutes)/60
1237         if seconds: value += float(seconds)/3600
1238         if hemisphere and hemisphere in "sw": value *= -1
1239         coordinates[coordinate] = math.radians(value)
1240     return tuple(coordinates)
1241
1242 def correlate():
1243     import codecs, csv, datetime, hashlib, os, re, sys, time, zipfile, zoneinfo
1244     if pyversion("3"): import configparser
1245     else: import ConfigParser as configparser
1246     for filename in os.listdir("."):
1247         if re.match("[0-9]{4}_Gaz_counties_national.zip$", filename):
1248             gcounties_an = filename
1249             gcounties_fn = filename[:-4] + ".txt"
1250         elif re.match("[0-9]{4}_Gaz_cousubs_national.zip$", filename):
1251             gcousubs_an = filename
1252             gcousubs_fn = filename[:-4] + ".txt"
1253         elif re.match("[0-9]{4}_Gaz_place_national.zip$", filename):
1254             gplace_an = filename
1255             gplace_fn = filename[:-4] + ".txt"
1256         elif re.match("[0-9]{4}_Gaz_zcta_national.zip$", filename):
1257             gzcta_an = filename
1258             gzcta_fn = filename[:-4] + ".txt"
1259         elif re.match("bp[0-9]{2}[a-z]{2}[0-9]{2}.dbx$", filename):
1260             cpfzcf_fn = filename
1261     nsdcccc_fn = "nsd_cccc.txt"
1262     ourairports_fn = "airports.csv"
1263     overrides_fn = "overrides.conf"
1264     overrideslog_fn = "overrides.log"
1265     slist_fn = "slist"
1266     zlist_fn = "zlist"
1267     qalog_fn = "qa.log"
1268     airports_fn = "airports"
1269     places_fn = "places"
1270     stations_fn = "stations"
1271     zctas_fn = "zctas"
1272     zones_fn = "zones"
1273     header = """\
1274 %s
1275 # generated by %s on %s from these public domain sources:
1276 #
1277 # https://www.census.gov/geographies/reference-files/time-series/geo/gazetteer-files.html
1278 # %s %s %s
1279 # %s %s %s
1280 # %s %s %s
1281 # %s %s %s
1282 #
1283 # https://www.weather.gov/gis/ZoneCounty/
1284 # %s %s %s
1285 #
1286 # https://tgftp.nws.noaa.gov/data/
1287 # %s %s %s
1288 #
1289 # https://ourairports.com/data/
1290 # %s %s %s
1291 #
1292 # ...and these manually-generated or hand-compiled adjustments:
1293 # %s %s %s
1294 # %s %s %s
1295 # %s %s %s\
1296 """ % (
1297         weather_copyright,
1298         os.path.basename( sys.argv[0] ),
1299         datetime.date.isoformat(
1300             datetime.datetime.utcfromtimestamp( int(os.environ.get('SOURCE_DATE_EPOCH', time.time())) )
1301         ),
1302         hashlib.md5( open(gcounties_an, "rb").read() ).hexdigest(),
1303         datetime.date.isoformat(
1304             datetime.datetime.utcfromtimestamp( os.path.getmtime(gcounties_an) )
1305         ),
1306         gcounties_an,
1307         hashlib.md5( open(gcousubs_an, "rb").read() ).hexdigest(),
1308         datetime.date.isoformat(
1309             datetime.datetime.utcfromtimestamp( os.path.getmtime(gcousubs_an) )
1310         ),
1311         gcousubs_an,
1312         hashlib.md5( open(gplace_an, "rb").read() ).hexdigest(),
1313         datetime.date.isoformat(
1314             datetime.datetime.utcfromtimestamp( os.path.getmtime(gplace_an) )
1315         ),
1316         gplace_an,
1317         hashlib.md5( open(gzcta_an, "rb").read() ).hexdigest(),
1318         datetime.date.isoformat(
1319             datetime.datetime.utcfromtimestamp( os.path.getmtime(gzcta_an) )
1320         ),
1321         gzcta_an,
1322         hashlib.md5( open(cpfzcf_fn, "rb").read() ).hexdigest(),
1323         datetime.date.isoformat(
1324             datetime.datetime.utcfromtimestamp( os.path.getmtime(cpfzcf_fn) )
1325         ),
1326         cpfzcf_fn,
1327         hashlib.md5( open(nsdcccc_fn, "rb").read() ).hexdigest(),
1328         datetime.date.isoformat(
1329             datetime.datetime.utcfromtimestamp( os.path.getmtime(nsdcccc_fn) )
1330         ),
1331         nsdcccc_fn,
1332         hashlib.md5( open(ourairports_fn, "rb").read() ).hexdigest(),
1333         datetime.date.isoformat(
1334             datetime.datetime.utcfromtimestamp( os.path.getmtime(ourairports_fn) )
1335         ),
1336         ourairports_fn,
1337         hashlib.md5( open(overrides_fn, "rb").read() ).hexdigest(),
1338         datetime.date.isoformat(
1339             datetime.datetime.utcfromtimestamp( os.path.getmtime(overrides_fn) )
1340         ),
1341         overrides_fn,
1342         hashlib.md5( open(slist_fn, "rb").read() ).hexdigest(),
1343         datetime.date.isoformat(
1344             datetime.datetime.utcfromtimestamp( os.path.getmtime(slist_fn) )
1345         ),
1346         slist_fn,
1347         hashlib.md5( open(zlist_fn, "rb").read() ).hexdigest(),
1348         datetime.date.isoformat(
1349             datetime.datetime.utcfromtimestamp( os.path.getmtime(zlist_fn) )
1350         ),
1351         zlist_fn
1352     )
1353     airports = {}
1354     places = {}
1355     stations = {}
1356     zctas = {}
1357     zones = {}
1358     message = "Reading %s:%s..." % (gcounties_an, gcounties_fn)
1359     sys.stdout.write(message)
1360     sys.stdout.flush()
1361     count = 0
1362     gcounties = zipfile.ZipFile(gcounties_an).open(gcounties_fn, "r")
1363     columns = gcounties.readline().decode("utf-8").strip().split("\t")
1364     for line in gcounties:
1365         fields = line.decode("utf-8").strip().split("\t")
1366         f_geoid = fields[ columns.index("GEOID") ].strip()
1367         f_name = fields[ columns.index("NAME") ].strip()
1368         f_usps = fields[ columns.index("USPS") ].strip()
1369         f_intptlat = fields[ columns.index("INTPTLAT") ].strip()
1370         f_intptlong = fields[ columns.index("INTPTLONG") ].strip()
1371         if f_geoid and f_name and f_usps and f_intptlat and f_intptlong:
1372             fips = "fips%s" % f_geoid
1373             if fips not in places: places[fips] = {}
1374             places[fips]["centroid"] = gecos(
1375                 "%s,%s" % (f_intptlat, f_intptlong)
1376             )
1377             places[fips]["description"] = "%s, %s" % (f_name, f_usps)
1378             count += 1
1379     gcounties.close()
1380     print("done (%s lines)." % count)
1381     message = "Reading %s:%s..." % (gcousubs_an, gcousubs_fn)
1382     sys.stdout.write(message)
1383     sys.stdout.flush()
1384     count = 0
1385     gcousubs = zipfile.ZipFile(gcousubs_an).open(gcousubs_fn, "r")
1386     columns = gcousubs.readline().decode("utf-8").strip().split("\t")
1387     for line in gcousubs:
1388         fields = line.decode("utf-8").strip().split("\t")
1389         f_geoid = fields[ columns.index("GEOID") ].strip()
1390         f_name = fields[ columns.index("NAME") ].strip()
1391         f_usps = fields[ columns.index("USPS") ].strip()
1392         f_intptlat = fields[ columns.index("INTPTLAT") ].strip()
1393         f_intptlong = fields[ columns.index("INTPTLONG") ].strip()
1394         if f_geoid and f_name and f_usps and f_intptlat and f_intptlong:
1395             fips = "fips%s" % f_geoid
1396             if fips not in places: places[fips] = {}
1397             places[fips]["centroid"] = gecos(
1398                 "%s,%s" % (f_intptlat, f_intptlong)
1399             )
1400             places[fips]["description"] = "%s, %s" % (f_name, f_usps)
1401             count += 1
1402     gcousubs.close()
1403     print("done (%s lines)." % count)
1404     message = "Reading %s:%s..." % (gplace_an, gplace_fn)
1405     sys.stdout.write(message)
1406     sys.stdout.flush()
1407     count = 0
1408     gplace = zipfile.ZipFile(gplace_an).open(gplace_fn, "r")
1409     columns = gplace.readline().decode("utf-8").strip().split("\t")
1410     for line in gplace:
1411         fields = line.decode("utf-8").strip().split("\t")
1412         f_geoid = fields[ columns.index("GEOID") ].strip()
1413         f_name = fields[ columns.index("NAME") ].strip()
1414         f_usps = fields[ columns.index("USPS") ].strip()
1415         f_intptlat = fields[ columns.index("INTPTLAT") ].strip()
1416         f_intptlong = fields[ columns.index("INTPTLONG") ].strip()
1417         if f_geoid and f_name and f_usps and f_intptlat and f_intptlong:
1418             fips = "fips%s" % f_geoid
1419             if fips not in places: places[fips] = {}
1420             places[fips]["centroid"] = gecos(
1421                 "%s,%s" % (f_intptlat, f_intptlong)
1422             )
1423             places[fips]["description"] = "%s, %s" % (f_name, f_usps)
1424             count += 1
1425     gplace.close()
1426     print("done (%s lines)." % count)
1427     message = "Reading %s..." % slist_fn
1428     sys.stdout.write(message)
1429     sys.stdout.flush()
1430     count = 0
1431     slist = codecs.open(slist_fn, "r", "utf-8")
1432     for line in slist:
1433         icao = line.split("#")[0].strip()
1434         if icao:
1435             stations[icao] = {
1436                 "metar": "https://tgftp.nws.noaa.gov/data/observations/"\
1437                     + "metar/decoded/%s.TXT" % icao.upper()
1438             }
1439             count += 1
1440     slist.close()
1441     print("done (%s lines)." % count)
1442     message = "Reading %s..." % nsdcccc_fn
1443     sys.stdout.write(message)
1444     sys.stdout.flush()
1445     count = 0
1446     nsdcccc = codecs.open(nsdcccc_fn, "r", "utf-8")
1447     for line in nsdcccc:
1448         line = str(line)
1449         fields = line.split(";")
1450         icao = fields[0].strip().lower()
1451         if icao in stations:
1452             description = []
1453             name = " ".join( fields[3].strip().title().split() )
1454             if name: description.append(name)
1455             st = fields[4].strip()
1456             if st: description.append(st)
1457             country = " ".join( fields[5].strip().title().split() )
1458             if country: description.append(country)
1459             if description:
1460                 stations[icao]["description"] = ", ".join(description)
1461             lat, lon = fields[7:9]
1462             if lat and lon:
1463                 stations[icao]["location"] = gecos( "%s,%s" % (lat, lon) )
1464             elif "location" not in stations[icao]:
1465                 lat, lon = fields[5:7]
1466                 if lat and lon:
1467                     stations[icao]["location"] = gecos( "%s,%s" % (lat, lon) )
1468         count += 1
1469     nsdcccc.close()
1470     print("done (%s lines)." % count)
1471     message = "Reading %s..." % ourairports_fn
1472     sys.stdout.write(message)
1473     sys.stdout.flush()
1474     count = 0
1475     ourairports = open(ourairports_fn, "r")
1476     for row in csv.reader(ourairports):
1477         icao = row[12].lower()
1478         if icao in stations:
1479             iata = row[13].lower()
1480             if len(iata) == 3: airports[iata] = { "station": icao }
1481             if "description" not in stations[icao]:
1482                 description = []
1483                 name = row[3]
1484                 if name: description.append(name)
1485                 municipality = row[10]
1486                 if municipality: description.append(municipality)
1487                 region = row[9]
1488                 country = row[8]
1489                 if region:
1490                     if "-" in region:
1491                         c,r = region.split("-", 1)
1492                         if c == country: region = r
1493                     description.append(region)
1494                 if country:
1495                     description.append(country)
1496                 if description:
1497                     stations[icao]["description"] = ", ".join(description)
1498             if "location" not in stations[icao]:
1499                 lat = row[4]
1500                 if lat:
1501                     lon = row[5]
1502                     if lon:
1503                         stations[icao]["location"] = gecos(
1504                             "%s,%s" % (lat, lon)
1505                         )
1506         count += 1
1507     ourairports.close()
1508     print("done (%s lines)." % count)
1509     message = "Reading %s..." % zlist_fn
1510     sys.stdout.write(message)
1511     sys.stdout.flush()
1512     count = 0
1513     zlist = codecs.open(zlist_fn, "r", "utf-8")
1514     for line in zlist:
1515         line = line.split("#")[0].strip()
1516         if line:
1517             zones[line] = {}
1518             count += 1
1519     zlist.close()
1520     print("done (%s lines)." % count)
1521     message = "Reading %s..." % cpfzcf_fn
1522     sys.stdout.write(message)
1523     sys.stdout.flush()
1524     count = 0
1525     cpfz = {}
1526     cpfzcf = codecs.open(cpfzcf_fn, "r", "utf-8")
1527     for line in cpfzcf:
1528         fields = line.strip().split("|")
1529         if len(fields) == 11 \
1530             and fields[0] and fields[1] and fields[9] and fields[10]:
1531             zone = "z".join( fields[:2] ).lower()
1532             if zone in zones:
1533                 state = fields[0]
1534                 description = fields[3].strip()
1535                 fips = "fips%s"%fields[6]
1536                 countycode = "%sc%s" % (state.lower(), fips[-3:])
1537                 if state:
1538                     zones[zone]["coastal_flood_statement"] = (
1539                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1540                         "flood/coastal/%s/%s.txt" % (state.lower(), zone))
1541                     zones[zone]["flash_flood_statement"] = (
1542                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1543                         "flash_flood/statement/%s/%s.txt"
1544                         % (state.lower(), countycode))
1545                     zones[zone]["flash_flood_warning"] = (
1546                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1547                         "flash_flood/warning/%s/%s.txt"
1548                         % (state.lower(), countycode))
1549                     zones[zone]["flash_flood_watch"] = (
1550                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1551                         "flash_flood/watch/%s/%s.txt" % (state.lower(), zone))
1552                     zones[zone]["flood_warning"] = (
1553                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1554                         "flood/warning/%s/%s.txt"
1555                         % (state.lower(), countycode))
1556                     zones[zone]["severe_thunderstorm_warning"] = (
1557                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1558                         "thunderstorm/%s/%s.txt" % (state.lower(), countycode))
1559                     zones[zone]["severe_weather_statement"] = (
1560                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1561                         "severe_weather_stmt/%s/%s.txt"
1562                         % (state.lower(), countycode))
1563                     zones[zone]["short_term_forecast"] = (
1564                         "https://tgftp.nws.noaa.gov/data/forecasts/nowcast/"
1565                         "%s/%s.txt" % (state.lower(), zone))
1566                     zones[zone]["special_weather_statement"] = (
1567                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1568                         "special_weather_stmt/%s/%s.txt"
1569                         % (state.lower(), zone))
1570                     zones[zone]["state_forecast"] = (
1571                         "https://tgftp.nws.noaa.gov/data/forecasts/state/"
1572                         "%s/%s.txt" % (state.lower(), zone))
1573                     zones[zone]["tornado"] = (
1574                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1575                         "tornado/%s/%s.txt" % (state.lower(), countycode))
1576                     zones[zone]["urgent_weather_message"] = (
1577                         "https://tgftp.nws.noaa.gov/data/watches_warnings/"
1578                         "non_precip/%s/%s.txt" % (state.lower(), zone))
1579                     zones[zone]["zone_forecast"] = (
1580                         "https://tgftp.nws.noaa.gov/data/forecasts/zone/"
1581                         "%s/%s.txt" % (state.lower(), zone))
1582                 tzcode = fields[7]
1583                 if tzcode == "A":
1584                     zones[zone]["tz"] = "US/Alaska"
1585                 elif tzcode == "AH":
1586                     zones[zone]["tz"] = "US/Aleutian"
1587                 elif tzcode in ("C", "CE", "CM"):
1588                     zones[zone]["tz"] = "US/Central"
1589                 elif tzcode in ("E", "e"):
1590                     zones[zone]["tz"] = "US/Eastern"
1591                 elif tzcode == "F":
1592                     zones[zone]["tz"] = "Pacific/Guadalcanal"
1593                 elif tzcode == "G":
1594                     zones[zone]["tz"] = "Pacific/Guam"
1595                 elif tzcode == "H":
1596                     zones[zone]["tz"] = "US/Hawaii"
1597                 elif tzcode == "J":
1598                     zones[zone]["tz"] = "Japan"
1599                 elif tzcode == "K":
1600                     zones[zone]["tz"] = "Pacific/Kwajalein"
1601                 elif tzcode in ("M", "MC", "MP"):
1602                     zones[zone]["tz"] = "US/Mountain"
1603                 elif tzcode == "m":
1604                     zones[zone]["tz"] = "US/Arizona"
1605                 elif tzcode == "P":
1606                     zones[zone]["tz"] = "US/Pacific"
1607                 elif tzcode == "S":
1608                     zones[zone]["tz"] = "US/Samoa"
1609                 elif tzcode == "V":
1610                     zones[zone]["tz"] = "America/Virgin"
1611                 else:
1612                     zones[zone]["tz"] = ""
1613                 county = fields[5]
1614                 if county:
1615                     if description.endswith(county):
1616                         description += " County"
1617                     else:
1618                         description += ", %s County" % county
1619                 description += ", %s, US" % state
1620                 zones[zone]["description"] = description
1621                 zones[zone]["centroid"] = gecos( ",".join( fields[9:11] ) )
1622                 if fips in places and not zones[zone]["centroid"]:
1623                     zones[zone]["centroid"] = places[fips]["centroid"]
1624         count += 1
1625     cpfzcf.close()
1626     print("done (%s lines)." % count)
1627     message = "Reading %s:%s..." % (gzcta_an, gzcta_fn)
1628     sys.stdout.write(message)
1629     sys.stdout.flush()
1630     count = 0
1631     gzcta = zipfile.ZipFile(gzcta_an).open(gzcta_fn, "r")
1632     columns = gzcta.readline().decode("utf-8").strip().split("\t")
1633     for line in gzcta:
1634         fields = line.decode("utf-8").strip().split("\t")
1635         f_geoid = fields[ columns.index("GEOID") ].strip()
1636         f_intptlat = fields[ columns.index("INTPTLAT") ].strip()
1637         f_intptlong = fields[ columns.index("INTPTLONG") ].strip()
1638         if f_geoid and f_intptlat and f_intptlong:
1639             if f_geoid not in zctas: zctas[f_geoid] = {}
1640             zctas[f_geoid]["centroid"] = gecos(
1641                 "%s,%s" % (f_intptlat, f_intptlong)
1642             )
1643             count += 1
1644     gzcta.close()
1645     print("done (%s lines)." % count)
1646     message = "Reading %s..." % overrides_fn
1647     sys.stdout.write(message)
1648     sys.stdout.flush()
1649     count = 0
1650     added = 0
1651     removed = 0
1652     changed = 0
1653     overrides = configparser.ConfigParser()
1654     overrides.read_file( codecs.open(overrides_fn, "r", "utf8") )
1655     overrideslog = []
1656     for section in overrides.sections():
1657         addopt = 0
1658         chgopt = 0
1659         if section.startswith("-"):
1660             section = section[1:]
1661             delete = True
1662         else: delete = False
1663         if re.match("[A-Za-z]{3}$", section):
1664             if delete:
1665                 if section in airports:
1666                     del( airports[section] )
1667                     logact = "removed airport %s" % section
1668                     removed += 1
1669                 else:
1670                     logact = "tried to remove nonexistent airport %s" % section
1671             else:
1672                 if section in airports:
1673                     logact = "changed airport %s" % section
1674                     changed += 1
1675                 else:
1676                     airports[section] = {}
1677                     logact = "added airport %s" % section
1678                     added += 1
1679                 for key,value in overrides.items(section):
1680                     if key in airports[section]: chgopt += 1
1681                     else: addopt += 1
1682                     if key in ("centroid", "location"):
1683                         airports[section][key] = eval(value)
1684                     else:
1685                         airports[section][key] = value
1686                 if addopt and chgopt:
1687                     logact += " (+%s/!%s options)" % (addopt, chgopt)
1688                 elif addopt: logact += " (+%s options)" % addopt
1689                 elif chgopt: logact += " (!%s options)" % chgopt
1690         elif re.match("[A-Za-z0-9]{4}$", section):
1691             if delete:
1692                 if section in stations:
1693                     del( stations[section] )
1694                     logact = "removed station %s" % section
1695                     removed += 1
1696                 else:
1697                     logact = "tried to remove nonexistent station %s" % section
1698             else:
1699                 if section in stations:
1700                     logact = "changed station %s" % section
1701                     changed += 1
1702                 else:
1703                     stations[section] = {}
1704                     logact = "added station %s" % section
1705                     added += 1
1706                 for key,value in overrides.items(section):
1707                     if key in stations[section]: chgopt += 1
1708                     else: addopt += 1
1709                     if key in ("centroid", "location"):
1710                         stations[section][key] = eval(value)
1711                     else:
1712                         stations[section][key] = value
1713                 if addopt and chgopt:
1714                     logact += " (+%s/!%s options)" % (addopt, chgopt)
1715                 elif addopt: logact += " (+%s options)" % addopt
1716                 elif chgopt: logact += " (!%s options)" % chgopt
1717         elif re.match("[0-9]{5}$", section):
1718             if delete:
1719                 if section in zctas:
1720                     del( zctas[section] )
1721                     logact = "removed zcta %s" % section
1722                     removed += 1
1723                 else:
1724                     logact = "tried to remove nonexistent zcta %s" % section
1725             else:
1726                 if section in zctas:
1727                     logact = "changed zcta %s" % section
1728                     changed += 1
1729                 else:
1730                     zctas[section] = {}
1731                     logact = "added zcta %s" % section
1732                     added += 1
1733                 for key,value in overrides.items(section):
1734                     if key in zctas[section]: chgopt += 1
1735                     else: addopt += 1
1736                     if key in ("centroid", "location"):
1737                         zctas[section][key] = eval(value)
1738                     else:
1739                         zctas[section][key] = value
1740                 if addopt and chgopt:
1741                     logact += " (+%s/!%s options)" % (addopt, chgopt)
1742                 elif addopt: logact += " (+%s options)" % addopt
1743                 elif chgopt: logact += " (!%s options)" % chgopt
1744         elif re.match("[A-Za-z]{2}[Zz][0-9]{3}$", section):
1745             if delete:
1746                 if section in zones:
1747                     del( zones[section] )
1748                     logact = "removed zone %s" % section
1749                     removed += 1
1750                 else:
1751                     logact = "tried to remove nonexistent zone %s" % section
1752             else:
1753                 if section in zones:
1754                     logact = "changed zone %s" % section
1755                     changed += 1
1756                 else:
1757                     zones[section] = {}
1758                     logact = "added zone %s" % section
1759                     added += 1
1760                 for key,value in overrides.items(section):
1761                     if key in zones[section]: chgopt += 1
1762                     else: addopt += 1
1763                     if key in ("centroid", "location"):
1764                         zones[section][key] = eval(value)
1765                     else:
1766                         zones[section][key] = value
1767                 if addopt and chgopt:
1768                     logact += " (+%s/!%s options)" % (addopt, chgopt)
1769                 elif addopt: logact += " (+%s options)" % addopt
1770                 elif chgopt: logact += " (!%s options)" % chgopt
1771         elif re.match("fips[0-9]+$", section):
1772             if delete:
1773                 if section in places:
1774                     del( places[section] )
1775                     logact = "removed place %s" % section
1776                     removed += 1
1777                 else:
1778                     logact = "tried to remove nonexistent place %s" % section
1779             else:
1780                 if section in places:
1781                     logact = "changed place %s" % section
1782                     changed += 1
1783                 else:
1784                     places[section] = {}
1785                     logact = "added place %s" % section
1786                     added += 1
1787                 for key,value in overrides.items(section):
1788                     if key in places[section]: chgopt += 1
1789                     else: addopt += 1
1790                     if key in ("centroid", "location"):
1791                         places[section][key] = eval(value)
1792                     else:
1793                         places[section][key] = value
1794                 if addopt and chgopt:
1795                     logact += " (+%s/!%s options)" % (addopt, chgopt)
1796                 elif addopt: logact += " (+%s options)" % addopt
1797                 elif chgopt: logact += " (!%s options)" % chgopt
1798         count += 1
1799         overrideslog.append("%s\n" % logact)
1800     overrideslog.sort()
1801     if os.path.exists(overrideslog_fn):
1802         os.rename(overrideslog_fn, "%s_old"%overrideslog_fn)
1803     overrideslog_fd = codecs.open(overrideslog_fn, "w", "utf8")
1804     import time
1805     overrideslog_fd.write(
1806         '# Copyright (c) %s Jeremy Stanley <fungi@yuggoth.org>. Permission to\n'
1807         '# use, copy, modify, and distribute this software is granted under terms\n'
1808         '# provided in the LICENSE file distributed with this software.\n\n'
1809         % time.gmtime().tm_year)
1810     overrideslog_fd.writelines(overrideslog)
1811     overrideslog_fd.close()
1812     print("done (%s overridden sections: +%s/-%s/!%s)." % (
1813         count,
1814         added,
1815         removed,
1816         changed
1817     ) )
1818     estimate = 2*len(places) + len(stations) + 2*len(zctas) + len(zones)
1819     print(
1820         "Correlating places, stations, ZCTAs and zones (upper bound is %s):" % \
1821             estimate
1822     )
1823     count = 0
1824     milestones = list( range(51) )
1825     message = "   "
1826     sys.stdout.write(message)
1827     sys.stdout.flush()
1828     for fips in places:
1829         centroid = places[fips]["centroid"]
1830         if centroid:
1831             station = closest(centroid, stations, "location", 0.1)
1832         if station[0]:
1833             places[fips]["station"] = station
1834             count += 1
1835             if not count%100:
1836                 level = int(50*count/estimate)
1837                 if level in milestones:
1838                     for remaining in milestones[:milestones.index(level)+1]:
1839                         if remaining%5:
1840                             message = "."
1841                             sys.stdout.write(message)
1842                             sys.stdout.flush()
1843                         else:
1844                             message = "%s%%" % (remaining*2,)
1845                             sys.stdout.write(message)
1846                             sys.stdout.flush()
1847                         milestones.remove(remaining)
1848         if centroid:
1849             zone = closest(centroid, zones, "centroid", 0.1)
1850         if zone[0]:
1851             places[fips]["zone"] = zone
1852             count += 1
1853             if not count%100:
1854                 level = int(50*count/estimate)
1855                 if level in milestones:
1856                     for remaining in milestones[:milestones.index(level)+1]:
1857                         if remaining%5:
1858                             message = "."
1859                             sys.stdout.write(message)
1860                             sys.stdout.flush()
1861                         else:
1862                             message = "%s%%" % (remaining*2,)
1863                             sys.stdout.write(message)
1864                             sys.stdout.flush()
1865                         milestones.remove(remaining)
1866     for station in stations:
1867         if "location" in stations[station]:
1868             location = stations[station]["location"]
1869             if location:
1870                 zone = closest(location, zones, "centroid", 0.1)
1871             if zone[0]:
1872                 stations[station]["zone"] = zone
1873                 count += 1
1874                 if not count%100:
1875                     level = int(50*count/estimate)
1876                     if level in milestones:
1877                         for remaining in milestones[:milestones.index(level)+1]:
1878                             if remaining%5:
1879                                 message = "."
1880                                 sys.stdout.write(message)
1881                                 sys.stdout.flush()
1882                             else:
1883                                 message = "%s%%" % (remaining*2,)
1884                                 sys.stdout.write(message)
1885                                 sys.stdout.flush()
1886                             milestones.remove(remaining)
1887     for zcta in zctas.keys():
1888         centroid = zctas[zcta]["centroid"]
1889         if centroid:
1890             station = closest(centroid, stations, "location", 0.1)
1891         if station[0]:
1892             zctas[zcta]["station"] = station
1893             count += 1
1894             if not count%100:
1895                 level = int(50*count/estimate)
1896                 if level in milestones:
1897                     for remaining in milestones[ : milestones.index(level)+1 ]:
1898                         if remaining%5:
1899                             message = "."
1900                             sys.stdout.write(message)
1901                             sys.stdout.flush()
1902                         else:
1903                             message = "%s%%" % (remaining*2,)
1904                             sys.stdout.write(message)
1905                             sys.stdout.flush()
1906                         milestones.remove(remaining)
1907         if centroid:
1908             zone = closest(centroid, zones, "centroid", 0.1)
1909         if zone[0]:
1910             zctas[zcta]["zone"] = zone
1911             count += 1
1912             if not count%100:
1913                 level = int(50*count/estimate)
1914                 if level in milestones:
1915                     for remaining in milestones[:milestones.index(level)+1]:
1916                         if remaining%5:
1917                             message = "."
1918                             sys.stdout.write(message)
1919                             sys.stdout.flush()
1920                         else:
1921                             message = "%s%%" % (remaining*2,)
1922                             sys.stdout.write(message)
1923                             sys.stdout.flush()
1924                         milestones.remove(remaining)
1925     for zone in zones.keys():
1926         if "centroid" in zones[zone]:
1927             centroid = zones[zone]["centroid"]
1928             if centroid:
1929                 station = closest(centroid, stations, "location", 0.1)
1930             if station[0]:
1931                 zones[zone]["station"] = station
1932                 count += 1
1933                 if not count%100:
1934                     level = int(50*count/estimate)
1935                     if level in milestones:
1936                         for remaining in milestones[:milestones.index(level)+1]:
1937                             if remaining%5:
1938                                 message = "."
1939                                 sys.stdout.write(message)
1940                                 sys.stdout.flush()
1941                             else:
1942                                 message = "%s%%" % (remaining*2,)
1943                                 sys.stdout.write(message)
1944                                 sys.stdout.flush()
1945                             milestones.remove(remaining)
1946     for remaining in milestones:
1947         if remaining%5:
1948             message = "."
1949             sys.stdout.write(message)
1950             sys.stdout.flush()
1951         else:
1952             message = "%s%%" % (remaining*2,)
1953             sys.stdout.write(message)
1954             sys.stdout.flush()
1955     print("\n   done (%s correlations)." % count)
1956     message = "Writing %s..." % airports_fn
1957     sys.stdout.write(message)
1958     sys.stdout.flush()
1959     count = 0
1960     if os.path.exists(airports_fn):
1961         os.rename(airports_fn, "%s_old"%airports_fn)
1962     airports_fd = codecs.open(airports_fn, "w", "utf8")
1963     airports_fd.write(header)
1964     for airport in sorted( airports.keys() ):
1965         airports_fd.write("\n\n[%s]" % airport)
1966         for key, value in sorted( airports[airport].items() ):
1967             if type(value) is float: value = "%.7f"%value
1968             elif type(value) is tuple:
1969                 elements = []
1970                 for element in value:
1971                     if type(element) is float: elements.append("%.7f"%element)
1972                     else: elements.append( repr(element) )
1973                 value = "(%s)"%", ".join(elements)
1974             airports_fd.write( "\n%s = %s" % (key, value) )
1975         count += 1
1976     airports_fd.write("\n")
1977     airports_fd.close()
1978     print("done (%s sections)." % count)
1979     message = "Writing %s..." % places_fn
1980     sys.stdout.write(message)
1981     sys.stdout.flush()
1982     count = 0
1983     if os.path.exists(places_fn):
1984         os.rename(places_fn, "%s_old"%places_fn)
1985     places_fd = codecs.open(places_fn, "w", "utf8")
1986     places_fd.write(header)
1987     for fips in sorted( places.keys() ):
1988         places_fd.write("\n\n[%s]" % fips)
1989         for key, value in sorted( places[fips].items() ):
1990             if type(value) is float: value = "%.7f"%value
1991             elif type(value) is tuple:
1992                 elements = []
1993                 for element in value:
1994                     if type(element) is float: elements.append("%.7f"%element)
1995                     else: elements.append( repr(element) )
1996                 value = "(%s)"%", ".join(elements)
1997             places_fd.write( "\n%s = %s" % (key, value) )
1998         count += 1
1999     places_fd.write("\n")
2000     places_fd.close()
2001     print("done (%s sections)." % count)
2002     message = "Writing %s..." % stations_fn
2003     sys.stdout.write(message)
2004     sys.stdout.flush()
2005     count = 0
2006     if os.path.exists(stations_fn):
2007         os.rename(stations_fn, "%s_old"%stations_fn)
2008     stations_fd = codecs.open(stations_fn, "w", "utf-8")
2009     stations_fd.write(header)
2010     for station in sorted( stations.keys() ):
2011         stations_fd.write("\n\n[%s]" % station)
2012         for key, value in sorted( stations[station].items() ):
2013             if type(value) is float: value = "%.7f"%value
2014             elif type(value) is tuple:
2015                 elements = []
2016                 for element in value:
2017                     if type(element) is float: elements.append("%.7f"%element)
2018                     else: elements.append( repr(element) )
2019                 value = "(%s)"%", ".join(elements)
2020             if type(value) is bytes:
2021                 value = value.decode("utf-8")
2022             stations_fd.write( "\n%s = %s" % (key, value) )
2023         count += 1
2024     stations_fd.write("\n")
2025     stations_fd.close()
2026     print("done (%s sections)." % count)
2027     message = "Writing %s..." % zctas_fn
2028     sys.stdout.write(message)
2029     sys.stdout.flush()
2030     count = 0
2031     if os.path.exists(zctas_fn):
2032         os.rename(zctas_fn, "%s_old"%zctas_fn)
2033     zctas_fd = codecs.open(zctas_fn, "w", "utf8")
2034     zctas_fd.write(header)
2035     for zcta in sorted( zctas.keys() ):
2036         zctas_fd.write("\n\n[%s]" % zcta)
2037         for key, value in sorted( zctas[zcta].items() ):
2038             if type(value) is float: value = "%.7f"%value
2039             elif type(value) is tuple:
2040                 elements = []
2041                 for element in value:
2042                     if type(element) is float: elements.append("%.7f"%element)
2043                     else: elements.append( repr(element) )
2044                 value = "(%s)"%", ".join(elements)
2045             zctas_fd.write( "\n%s = %s" % (key, value) )
2046         count += 1
2047     zctas_fd.write("\n")
2048     zctas_fd.close()
2049     print("done (%s sections)." % count)
2050     message = "Writing %s..." % zones_fn
2051     sys.stdout.write(message)
2052     sys.stdout.flush()
2053     count = 0
2054     if os.path.exists(zones_fn):
2055         os.rename(zones_fn, "%s_old"%zones_fn)
2056     zones_fd = codecs.open(zones_fn, "w", "utf8")
2057     zones_fd.write(header)
2058     for zone in sorted( zones.keys() ):
2059         zones_fd.write("\n\n[%s]" % zone)
2060         for key, value in sorted( zones[zone].items() ):
2061             if type(value) is float: value = "%.7f"%value
2062             elif type(value) is tuple:
2063                 elements = []
2064                 for element in value:
2065                     if type(element) is float: elements.append("%.7f"%element)
2066                     else: elements.append( repr(element) )
2067                 value = "(%s)"%", ".join(elements)
2068             zones_fd.write( "\n%s = %s" % (key, value) )
2069         count += 1
2070     zones_fd.write("\n")
2071     zones_fd.close()
2072     print("done (%s sections)." % count)
2073     message = "Starting QA check..."
2074     sys.stdout.write(message)
2075     sys.stdout.flush()
2076     airports = configparser.ConfigParser()
2077     if pyversion("3"):
2078         airports.read(airports_fn, encoding="utf-8")
2079     else:
2080         airports.read(airports_fn)
2081     places = configparser.ConfigParser()
2082     if pyversion("3"):
2083         places.read(places_fn, encoding="utf-8")
2084     else:
2085         places.read(places_fn)
2086     stations = configparser.ConfigParser()
2087     if pyversion("3"):
2088         stations.read(stations_fn, encoding="utf-8")
2089     else:
2090         stations.read(stations_fn)
2091     zctas = configparser.ConfigParser()
2092     if pyversion("3"):
2093         zctas.read(zctas_fn, encoding="utf-8")
2094     else:
2095         zctas.read(zctas_fn)
2096     zones = configparser.ConfigParser()
2097     if pyversion("3"):
2098         zones.read(zones_fn, encoding="utf-8")
2099     else:
2100         zones.read(zones_fn)
2101     qalog = []
2102     places_nocentroid = 0
2103     places_nodescription = 0
2104     for place in sorted( places.sections() ):
2105         if not places.has_option(place, "centroid"):
2106             qalog.append("%s: no centroid\n" % place)
2107             places_nocentroid += 1
2108         if not places.has_option(place, "description"):
2109             qalog.append("%s: no description\n" % place)
2110             places_nodescription += 1
2111     stations_nodescription = 0
2112     stations_nolocation = 0
2113     stations_nometar = 0
2114     for station in sorted( stations.sections() ):
2115         if not stations.has_option(station, "description"):
2116             qalog.append("%s: no description\n" % station)
2117             stations_nodescription += 1
2118         if not stations.has_option(station, "location"):
2119             qalog.append("%s: no location\n" % station)
2120             stations_nolocation += 1
2121         if not stations.has_option(station, "metar"):
2122             qalog.append("%s: no metar\n" % station)
2123             stations_nometar += 1
2124     airports_badstation = 0
2125     airports_nostation = 0
2126     for airport in sorted( airports.sections() ):
2127         if not airports.has_option(airport, "station"):
2128             qalog.append("%s: no station\n" % airport)
2129             airports_nostation += 1
2130         else:
2131             station = airports.get(airport, "station")
2132             if station not in stations.sections():
2133                 qalog.append( "%s: bad station %s\n" % (airport, station) )
2134                 airports_badstation += 1
2135     zctas_nocentroid = 0
2136     for zcta in sorted( zctas.sections() ):
2137         if not zctas.has_option(zcta, "centroid"):
2138             qalog.append("%s: no centroid\n" % zcta)
2139             zctas_nocentroid += 1
2140     zones_nocentroid = 0
2141     zones_nodescription = 0
2142     zones_notz = 0
2143     zones_noforecast = 0
2144     zones_overlapping = 0
2145     zonetable = {}
2146     for zone in zones.sections():
2147         if zones.has_option(zone, "centroid"):
2148             zonetable[zone] = {
2149                 "centroid": eval( zones.get(zone, "centroid") )
2150             }
2151     for zone in sorted( zones.sections() ):
2152         if zones.has_option(zone, "centroid"):
2153             zonetable_local = zonetable.copy()
2154             del( zonetable_local[zone] )
2155             centroid = eval( zones.get(zone, "centroid") )
2156             if centroid:
2157                 nearest = closest(centroid, zonetable_local, "centroid", 0.1)
2158             if nearest[1]*radian_to_km < 1:
2159                 qalog.append( "%s: within one km of %s\n" % (
2160                     zone,
2161                     nearest[0]
2162                 ) )
2163                 zones_overlapping += 1
2164         else:
2165             qalog.append("%s: no centroid\n" % zone)
2166             zones_nocentroid += 1
2167         if not zones.has_option(zone, "description"):
2168             qalog.append("%s: no description\n" % zone)
2169             zones_nodescription += 1
2170         if not zones.has_option(zone, "tz") or not zones.get(
2171                 zone, "tz") in zoneinfo.available_timezones():
2172             qalog.append("%s: no time zone\n" % zone)
2173             zones_notz += 1
2174         if not zones.has_option(zone, "zone_forecast"):
2175             qalog.append("%s: no forecast\n" % zone)
2176             zones_noforecast += 1
2177     if os.path.exists(qalog_fn):
2178         os.rename(qalog_fn, "%s_old"%qalog_fn)
2179     qalog_fd = codecs.open(qalog_fn, "w", "utf8")
2180     import time
2181     qalog_fd.write(
2182         '# Copyright (c) %s Jeremy Stanley <fungi@yuggoth.org>. Permission to\n'
2183         '# use, copy, modify, and distribute this software is granted under terms\n'
2184         '# provided in the LICENSE file distributed with this software.\n\n'
2185         % time.gmtime().tm_year)
2186     qalog_fd.writelines(qalog)
2187     qalog_fd.close()
2188     if qalog:
2189         print("issues found (see %s for details):"%qalog_fn)
2190         if airports_badstation:
2191             print("   %s airports with invalid station"%airports_badstation)
2192         if airports_nostation:
2193             print("   %s airports with no station"%airports_nostation)
2194         if places_nocentroid:
2195             print("   %s places with no centroid"%places_nocentroid)
2196         if places_nodescription:
2197             print("   %s places with no description"%places_nodescription)
2198         if stations_nodescription:
2199             print("   %s stations with no description"%stations_nodescription)
2200         if stations_nolocation:
2201             print("   %s stations with no location"%stations_nolocation)
2202         if stations_nometar:
2203             print("   %s stations with no METAR"%stations_nometar)
2204         if zctas_nocentroid:
2205             print("   %s ZCTAs with no centroid"%zctas_nocentroid)
2206         if zones_nocentroid:
2207             print("   %s zones with no centroid"%zones_nocentroid)
2208         if zones_nodescription:
2209             print("   %s zones with no description"%zones_nodescription)
2210         if zones_notz:
2211             print("   %s zones with no time zone"%zones_notz)
2212         if zones_noforecast:
2213             print("   %s zones with no forecast"%zones_noforecast)
2214         if zones_overlapping:
2215             print("   %s zones within one km of another"%zones_overlapping)
2216     else: print("no issues found.")
2217     print("Indexing complete!")