run.py 37.4 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090
# coding=utf-8

import StringIO
import datetime
import gzip
import json
import logging
import random
import tarfile
import time
import urllib
import cdf
from csv import writer as csv_writer
from math import sqrt
from os import environ, remove as removefile
from os.path import isfile, join, abspath, dirname

from flask import Flask
from flask import request
from flask import url_for, send_from_directory, abort as abort_flask
from jinja2 import Environment, FileSystemLoader, Markup
from netCDF4 import Dataset, date2num
from yaml import load as yaml_load

# PATH RELATIVITY #############################################################

THIS_DIRECTORY = dirname(abspath(__file__))


def get_path(relative_path):
    """Get an absolute path from the relative path to this script directory."""
    return abspath(join(THIS_DIRECTORY, relative_path))


# COLLECT GLOBAL INFORMATION FROM SOURCES #####################################

# VERSION
with open(get_path('../VERSION'), 'r') as version_file:
    version = version_file.read().strip()

# CONFIG
with open(get_path('../config.yml'), 'r') as config_file:
    config = yaml_load(config_file.read())

FILE_DATE_FMT = "%Y-%m-%dT%H:%M:%S"


# LOGGING #####################################################################

LOG_FILE = get_path('run.log')

log = logging.getLogger("HelioPropa")
log.setLevel(logging.DEBUG)
# log.setLevel(logging.ERROR)                        # <-- set log level here !
logHandler = logging.FileHandler(LOG_FILE)
logHandler.setFormatter(logging.Formatter(
    "%(asctime)s - %(levelname)s - %(message)s"
))
log.addHandler(logHandler)


# HARDCODED CONFIGURATION #####################################################

# Absolute path to the data cache directory
CACHE_DIR = get_path('../cache')

# These two configs are not in the YAML config because adding a new parameter
# will not work as-is, you'll have to edit some netcdf-related code.

# The slugs of the available parameters in the generated CSV files.
# The order matters. If you change this you also need to change the
# innermost loop of `get_data_for_target`.
# The javascript knows the targets' properties under these names.
PROPERTIES = ('time', 'vrad', 'vtan', 'vtot', 'btan', 'temp', 'pdyn', 'dens',
              'angl', 'xhee', 'yhee')

# The parameters that the users can handle.
# The slug MUST be one of the properties above.
PARAMETERS = {
    'pdyn': {
        'slug': 'pdyn',
        'name': 'Dyn. Pressure',
        'title': 'The dynamic pressure.',
        'units': 'nPa',
        'active': True,
        'position': 10,
    },
    'vtot': {
        'slug': 'vtot',
        'name': 'Velocity',
        'title': 'The velocity of the particles.',
        'units': 'km/s',
        'active': False,
        'position': 20,
    },
    'btan': {
        'slug': 'btan',
        'name': 'B Tangential',
        'title': 'B Tangential.',
        'units': 'nT',
        'active': False,
        'position': 30,
    },
    'temp': {
        'slug': 'temp',
        'name': 'Temperature',
        'title': 'The temperature.',
        'units': 'eV',
        'active': False,
        'position': 40,
    },
    'dens': {
        'slug': 'dens',
        'name': 'Density',
        'title': 'The density N.',
        'units': 'cm^-3',
        'active': False,
        'position': 50,
    },
    'angl': {
        'slug': 'angl',
        'name': 'Angle T-S-E',
        'title': 'Angle Target-Sun-Earth.',
        'units': 'deg',
        'active': False,
        'position': 60,
    },
}


# SETUP FLASK ENGINE ##########################################################

app = Flask(__name__, root_path=THIS_DIRECTORY)
app.debug = environ.get('DEBUG') == 'true'
if app.debug:
    log.info("Starting Flask app IN DEBUG MODE...")
else:
    log.info("Starting Flask app...")


# SETUP JINJA2 TEMPLATE ENGINE ################################################

def static_global(filename):
    return url_for('static', filename=filename)


def shuffle_filter(seq):
    """
    This shuffles the sequence it is applied to.
    Jinja2 _should_ provide this.
    """
    try:
        result = list(seq)
        random.shuffle(result)
        return result
    except:
        return seq


def markdown_filter(value, nl2br=False, p=True):
    """
    Converts markdown into html.
    nl2br: set to True to replace line breaks with <br> tags
    p: set to False to remove the enclosing <p></p> tags
    """
    from markdown import markdown
    from markdown.extensions.nl2br import Nl2BrExtension
    from markdown.extensions.abbr import AbbrExtension
    extensions = [AbbrExtension()]
    if nl2br is True:
        extensions.append(Nl2BrExtension())
    markdowned = markdown(value, output_format='html5', extensions=extensions)
    if p is False:
        markdowned = markdowned.replace(r"<p>", "").replace(r"</p>", "")
    return markdowned


_js_escapes = {
        '\\': '\\u005C',
        '\'': '\\u0027',
        '"': '\\u0022',
        '>': '\\u003E',
        '<': '\\u003C',
        '&': '\\u0026',
        '=': '\\u003D',
        '-': '\\u002D',
        ';': '\\u003B',
        u'\u2028': '\\u2028',
        u'\u2029': '\\u2029'
}
# Escape every ASCII character with a value less than 32.
_js_escapes.update(('%c' % z, '\\u%04X' % z) for z in xrange(32))


def escapejs_filter(value):
    escaped = []
    for letter in value:
        if letter in _js_escapes:
            escaped.append(_js_escapes[letter])
        else:
            escaped.append(letter)

    return Markup("".join(escaped))

tpl_engine = Environment(loader=FileSystemLoader([get_path('view')]),
                         trim_blocks=True,
                         lstrip_blocks=True)

tpl_engine.globals.update(
    url_for=url_for,
    static=static_global,
)

tpl_engine.filters['markdown'] = markdown_filter
tpl_engine.filters['md'] = markdown_filter
tpl_engine.filters['shuffle'] = shuffle_filter
tpl_engine.filters['escapejs'] = escapejs_filter

tpl_global_vars = {
    'request': request,
    'version': version,
    'config': config,
    'now': datetime.datetime.now(),
}


# HELPERS #####################################################################

def abort(code, message):
    log.error(message)
    abort_flask(code, message)


def render_view(view, context=None):
    """
    A simple helper to render [view] template with [context] vars.
    It automatically adds the global template vars defined above, too.
    It returns a string, usually the HTML contents to display.
    """
    context = {} if context is None else context
    return tpl_engine.get_template(view).render(
        dict(tpl_global_vars.items() + context.items())
    )


# def render_page(page, title="My Page", context=None):
#     """
#     A simple helper to render the md_page.html template with [context] vars &
#     the additional contents of `page/[page].md` in the `md_page` variable.
#     It automagically adds the global template vars defined above, too.
#     It returns a string, usually the HTML contents to display.
#     """
#     if context is None:
#         context = {}
#     context['title'] = title
#     context['md_page'] = ''
#     with file(get_path('page/%s.md' % page)) as f:
#         context['md_page'] = f.read()
#     return tpl_engine.get_template('md_page.html').render(
#         dict(tpl_global_vars.items() + context.items())
#     )


def is_list_in_list(needle, haystack):
    for n in needle:
        if n not in haystack:
            return False
    return True


def round_time(dt=None, round_to=60):
    """
    Round a datetime object to any time laps in seconds
    dt : datetime.datetime object, default now.
    roundTo : Closest number of seconds to round to, default 1 minute.
    """
    if dt is None:
        dt = datetime.datetime.now()
    seconds = (dt.replace(tzinfo=None) - dt.min).seconds
    rounding = (seconds + round_to / 2) // round_to * round_to
    return dt + datetime.timedelta(0, rounding-seconds, -dt.microsecond)


def datetime_from_list(time_list):
    """
    Datetimes in retrieved CDFs are stored as lists of numbers,
    with DayOfYear starting at 0. We want it starting at 1 because it's what
    vendor parsers use, both in python and javascript.
    """
    # Day Of Year starts at 0, but for our datetime parser it starts at 1
    doy = '{:03d}'.format(int(''.join(time_list[4:7])) + 1)
    return datetime.datetime.strptime(
        "%s%s%s" % (''.join(time_list[0:4]), doy, ''.join(time_list[7:])),
        "%Y%j%H%M%S%f"
    )


def get_local_filename(url):
    """
    Build the local cache filename for the distant file
    :param url: string
    :return: string
    """
    from slugify import slugify
    n = len('http://')
    if url.startswith('https'):
        n += 1
    s = url[n:]
    return slugify(s)


def get_target_config(slug):
    for s in config['targets']:  # dumb
        if s['slug'] == slug:
            return s
    raise Exception("No target found in configuration for '%s'." % slug)


def check_target_config(slug):
    get_target_config(slug)


def retrieve_amda_netcdf(orbiter, what, started_at, stopped_at):
    """
    Handles remote querying Myriam's API, downloading, extracting and caching
    the netCDF files.
    :param orbiter: key of the source in the YAML config
    :param what: either 'model' or 'orbit', a key in the config of the source
    :param started_at:
    :param stopped_at:
    :return: a list of local file paths to netCDF (.nc) files
    """

    url = config['amda'].format(
        dataSet=what,
        startTime=started_at.isoformat(),
        stopTime=stopped_at.isoformat()
    )
    log.info("Fetching remote gzip files list at '%s'." % url)
    retries = 0
    success = False
    errors = []
    remote_gzip_files = []
    while not success and retries < 3:
        try:
            response = urllib.urlopen(url)
            remote_gzip_files = json.loads(response.read())
            if not remote_gzip_files:
                raise Exception("Failed to fetch data at '%s'." % url)
            if remote_gzip_files == 'NODATASET':
                raise Exception("API says there's no dataset at '%s'." % url)
            if remote_gzip_files == 'ERROR':
                raise Exception("API returned an error at '%s'." % url)
            if remote_gzip_files == ['OUTOFTIME']:  # it happens
                return []
                # raise Exception("API says it's out of time at '%s'." % url)
            success = True
        except Exception as e:
            log.warn("Failed (%d/3) '%s' : %s" % (retries+1, url, e.message))
            remote_gzip_files = []
            errors.append(e)
        finally:
            retries += 1
    if not remote_gzip_files:
        abort(400, "Failed to fetch gzip files list for %s at '%s' : %s" %
                   (orbiter, url, errors))
    else:
        remote_gzip_files = list(set(remote_gzip_files))

    log.debug("Fetched remote gzip files list : %s." % str(remote_gzip_files))

    local_gzip_files = []
    for remote_gzip_file in remote_gzip_files:
        # hotfixes to remove when fixed upstream @Myriam
        if remote_gzip_file in ['OUTOFTIME', 'ERROR']:
            continue  # sometimes half the response is okay, the other not
        if remote_gzip_file.endswith('/.gz'):
            continue  # this is just a plain bug
        remote_gzip_file = remote_gzip_file.replace('cdpp1', 'cdpp', 1)
        ################################################
        local_gzip_file = join(CACHE_DIR, get_local_filename(remote_gzip_file))
        local_gzip_files.append(local_gzip_file)
        if not isfile(local_gzip_file):
            log.debug("Retrieving '%s'..." % local_gzip_file)
            urllib.urlretrieve(remote_gzip_file, local_gzip_file)
            log.debug("Retrieved '%s'." % local_gzip_file)
        else:
            log.debug("Found '%s' in the cache." % local_gzip_file)

    local_netc_files = []
    for local_gzip_file in local_gzip_files:
        local_netc_file = local_gzip_file[0:-3]
        log.debug("Unzipping '%s'..." % local_gzip_file)
        success = True
        try:
            with gzip.open(local_gzip_file, 'rb') as f:
                file_content = f.read()
                with open(local_netc_file, 'w+b') as g:
                    g.write(file_content)
        except Exception as e:
            success = False
            log.error("Cannot process gz file '%s' from '%s' : %s" %
                      (local_gzip_file, url, e))
            # Sometimes, the downloaded gz is corrupted, and CRC checks fail.
            # We want to delete the local gz file and try again next time.
            removefile(local_gzip_file)
        if success:
            local_netc_files.append(local_netc_file)
            log.debug("Unzipped '%s'." % local_gzip_file)

    return list(set(local_netc_files))  # remove possible dupes


def get_data_for_target(target_config, started_at, stopped_at):
    """
    :return: dict whose keys are datetime as str, values tuples of data
    """
    log.debug("Grabbing data for '%s'..." % target_config['slug'])

    try:
        models = target_config['models']
    except Exception as e:
        abort(500, "Invalid model configuration for '%s' : %s"
              % (target_config['slug'], str(e)))
    try:
        orbits = target_config['orbit']['models']
    except Exception as e:
        abort(500, "Invalid orbit configuration for '%s' : %s"
              % (target_config['slug'], str(e)))

    def _sta_sto(_cnf, _sta, _sto):
        if 'started_at' in _cnf:
            _s0 = datetime.datetime.strptime(_cnf['started_at'], FILE_DATE_FMT)
            _s0 = max(_s0, _sta)
        else:
            _s0 = _sta
        if 'stopped_at' in _cnf:
            _s1 = datetime.datetime.strptime(_cnf['stopped_at'], FILE_DATE_FMT)
            _s1 = min(_s1, _sto)
        else:
            _s1 = _sto
        return _s0, _s1

    precision = "%Y-%m-%dT%H"  # model and orbits times are only equal-ish
    orbit_data = {}  # keys are datetime as str, values arrays of XY

    for orbit in orbits:
        s0, s1 = _sta_sto(orbit, started_at, stopped_at)

        orbit_files = retrieve_amda_netcdf(
            target_config['slug'], orbit['slug'], s0, s1
        )
        for orbit_file in orbit_files:
            log.debug("%s: opening orbit NETCDF4 '%s'..." %
                      (target_config['name'], orbit_file))
            cdf_handle = Dataset(orbit_file, "r", format="NETCDF4")
            times = cdf_handle.variables['Time']  # YYYY DOY HH MM SS .ms
            try:
                data_hee = cdf_handle.variables['HEE']
            except KeyError:
                data_hee = cdf_handle.variables['XYZ_HEE']  # p67 uses this

            log.debug("%s: aggregating data from '%s'..." %
                      (target_config['name'], orbit_file))
            for time, datum_hee in zip(times, data_hee):
                try:
                    dtime = datetime_from_list(time)
                except Exception as e:
                    log.error("Failed to parse time from %s." % time)
                    raise e
                if s0 <= dtime <= s1:
                    dkey = round_time(dtime, 60*60).strftime(precision)
                    orbit_data[dkey] = datum_hee
            cdf_handle.close()

    all_data = {}  # keys are datetime as str, values tuples of data
    for model in models:
        s0, s1 = _sta_sto(model, started_at, stopped_at)
        model_files = retrieve_amda_netcdf(
            target_config['slug'], model['slug'], s0, s1
        )
        for model_file in model_files:
            # Time, StartTime, StopTime, V, B, N, T, Delta_angle, P_dyn
            log.debug("%s: opening model NETCDF4 '%s'..." %
                      (target_config['name'], model_file))
            cdf_handle = Dataset(model_file, "r", format="NETCDF4")
            times = cdf_handle.variables['Time']  # YYYY DOY HH MM SS .ms
            data_v = cdf_handle.variables['V']
            data_b = cdf_handle.variables['B']
            data_t = cdf_handle.variables['T']
            data_n = cdf_handle.variables['N']
            data_p = cdf_handle.variables['P_dyn']
            data_d = cdf_handle.variables['Delta_angle']
            log.debug("%s: aggregating data from '%s'..." %
                      (target_config['name'], model_file))
            for time, datum_v, datum_b, datum_t, datum_n, datum_p, datum_d \
                    in zip(times, data_v, data_b, data_t, data_n, data_p, data_d):
                vrad = datum_v[0]
                vtan = datum_v[1]
                try:
                    dtime = datetime_from_list(time)
                except Exception as e:
                    log.error("Failed to parse time from %s." % time)
                    raise e
                if s0 <= dtime <= s1:
                    dkey = round_time(dtime, 60*60).strftime(precision)
                    x_hee = None
                    y_hee = None
                    if dkey in orbit_data:
                        x_hee = orbit_data[dkey][0]
                        y_hee = orbit_data[dkey][1]
                    all_data[dkey] = (
                        dtime.strftime("%Y-%m-%dT%H:%M:%S+00:00"),
                        vrad, vtan, sqrt(vrad * vrad + vtan * vtan),
                        datum_b, datum_t, datum_n, datum_p, datum_d,
                        x_hee, y_hee
                    )
            cdf_handle.close()

    return all_data


def generate_csv_contents(target_slug, started_at, stopped_at):
    target_config = get_target_config(target_slug)
    log.debug("Crunching CSV contents for '%s'..." % target_config['name'])
    si = StringIO.StringIO()
    cw = csv_writer(si)
    cw.writerow(PROPERTIES)

    all_data = get_data_for_target(target_config, started_at, stopped_at)

    log.debug("Writing and sorting CSV for '%s'..." % target_config['slug'])
    for dkey in sorted(all_data):
        cw.writerow(all_data[dkey])

    log.info("Generated CSV contents for '%s'." % target_config['slug'])
    return si.getvalue()


def generate_csv_file_if_needed(target_slug, started_at, stopped_at):
    filename = "%s_%s_%s.csv" % (target_slug,
                                 started_at.strftime(FILE_DATE_FMT),
                                 stopped_at.strftime(FILE_DATE_FMT))
    local_csv_file = join(CACHE_DIR, filename)

    generate = True
    if isfile(local_csv_file):
        # It need to have more than one line to not be empty (headers)
        with open(local_csv_file) as f:
            cnt = 0
            for _ in f:
                cnt += 1
                if cnt > 1:
                    generate = False
                    break

    if generate:
        log.info("Generating CSV '%s'..." % local_csv_file)
        try:
            with open(local_csv_file, mode="w+") as f:
                f.write(generate_csv_contents(target_slug,
                                              started_at=started_at,
                                              stopped_at=stopped_at))
            log.info("Generation of '%s' done." % filename)
        except Exception as e:
            log.error(e)
            if isfile(local_csv_file):
                log.warn("Removing failed CSV '%s'..." % local_csv_file)
                removefile(local_csv_file)
            abort(500, "Failed creating CSV '%s' : %s" % (filename, e))


def remove_all_files(in_directory):
    """
    Will throw if something horrible happens.
    Does not remove recursively (could be done with os.walk if needed).
    Does not remove directories either.
    :param in_directory: absolute path to directory
    :return:
    """
    import os

    if not os.path.isdir(in_directory):
        raise ValueError("No directory to clean at '%s'.")

    removed_files = []
    for file_name in os.listdir(in_directory):
        file_path = os.path.join(in_directory, file_name)
        if os.path.isfile(file_path):
            os.remove(file_path)
            removed_files.append(file_path)

    return removed_files


def remove_files_created_before(date, in_directory):
    """
    Will throw if something horrible happens.
    Does not remove recursively (could be done with os.walk if needed).
    Does not remove directories either.
    :param date: datetime object
    :param in_directory: absolute path to directory
    :return:
    """
    import os
    import time

    secs = time.mktime(date.timetuple())

    if not os.path.isdir(in_directory):
        raise ValueError("No directory to clean at '%s'.")

    removed_files = []
    for file_name in os.listdir(in_directory):
        file_path = os.path.join(in_directory, file_name)
        if os.path.isfile(file_path):
            t = os.stat(file_path)
            if t.st_ctime < secs:
                os.remove(file_path)
                removed_files.append(file_path)

    return removed_files


def get_hit_counter():
    hit_count_path = get_path("../VISITS")

    if isfile(hit_count_path):
        hit_count = int(open(hit_count_path).read())
    else:
        hit_count = 1

    return hit_count


def increment_hit_counter():
    hit_count_path = get_path("../VISITS")

    if isfile(hit_count_path):
        hit_count = int(open(hit_count_path).read())
        hit_count += 1
    else:
        hit_count = 1

    hit_counter_file = open(hit_count_path, 'w')
    hit_counter_file.write(str(hit_count))
    hit_counter_file.close()

    return hit_count


tpl_global_vars['visits'] = get_hit_counter()


# ROUTING #####################################################################

@app.route('/favicon.ico')
def favicon():  # we want it served from the root, not from static/
    return send_from_directory(
        join(app.root_path, 'static', 'img'),
        'favicon.ico', mimetype='image/vnd.microsoft.icon'
    )


@app.route("/")
@app.route("/home.html")
@app.route("/index.html")
def home():
    increment_hit_counter()
    parameters = PARAMETERS.values()
    parameters.sort(key=lambda x: x['position'])
    return render_view('home.html.jinja2', {
        'targets': config['targets'],
        'parameters': parameters,
        'planets': [s for s in config['targets'] if s['type'] == 'planet'],
        'probes':  [s for s in config['targets'] if s['type'] == 'probe'],
        'comets':  [s for s in config['targets'] if s['type'] == 'comet'],
        'visits':  get_hit_counter(),
    })


@app.route("/<target>_<started_at>_<stopped_at>.csv")
def download_target_csv(target, started_at, stopped_at):
    """
    Grab data and orbit data for the specified `target`,
    rearrange it and return it as a CSV file.
    `started_at` and `stopped_at` should be UTC.
    """
    check_target_config(target)
    try:
        started_at = datetime.datetime.strptime(started_at, FILE_DATE_FMT)
    except:
        abort(400, "Invalid started_at parameter : '%s'." % started_at)
    try:
        stopped_at = datetime.datetime.strptime(stopped_at, FILE_DATE_FMT)
    except:
        abort(400, "Invalid stopped_at parameter : '%s'." % stopped_at)

    filename = "%s_%s_%s.csv" % (target,
                                 started_at.strftime(FILE_DATE_FMT),
                                 stopped_at.strftime(FILE_DATE_FMT))
    local_csv_file = join(CACHE_DIR, filename)
    generate_csv_file_if_needed(target, started_at, stopped_at)
    if not isfile(local_csv_file):
        abort(500, "Could not cache CSV file at '%s'." % local_csv_file)

    return send_from_directory(CACHE_DIR, filename)


@app.route("/<targets>_<started_at>_<stopped_at>.tar.gz")
def download_targets_tarball(targets, started_at, stopped_at):
    """
    Grab data and orbit data for each of the specified `targets`,
    in their own CSV file, and make a tarball of them.
    `started_at` and `stopped_at` should be UTC strings.

    Note: we do not use this route anymore, but let's keep it shelved for now.

    targets: string list of targets' slugs, separated by `-`.
    """
    separator = '-'
    targets = targets.split(separator)
    targets.sort()
    targets_configs = []
    for target in targets:
        if not target:
            abort(400, "Invalid targets format : `%s`." % targets)
        targets_configs.append(get_target_config(target))
    if 0 == len(targets_configs):
        abort(400, "No valid targets specified. What are you doing?")

    try:
        started_at = datetime.datetime.strptime(started_at, FILE_DATE_FMT)
    except:
        abort(400, "Invalid started_at parameter : '%s'." % started_at)
    try:
        stopped_at = datetime.datetime.strptime(stopped_at, FILE_DATE_FMT)
    except:
        abort(400, "Invalid stopped_at parameter : '%s'." % stopped_at)
    sta = started_at.strftime(FILE_DATE_FMT)
    sto = stopped_at.strftime(FILE_DATE_FMT)

    gzip_filename = "%s_%s_%s.tar.gz" % (separator.join(targets), sta, sto)
    local_gzip_file = join(CACHE_DIR, gzip_filename)

    if not isfile(local_gzip_file):
        log.debug("Creating the CSV files for the tarball...")
        for target_config in targets_configs:
            filename = "%s_%s_%s.csv" % (target_config['slug'], sta, sto)
            local_csv_file = join(CACHE_DIR, filename)
            if not isfile(local_csv_file):
                with open(local_csv_file, mode="w+") as f:
                    f.write(generate_csv_contents(target_config['slug'],
                                                  started_at=started_at,
                                                  stopped_at=stopped_at))

        log.debug("Creating the tarball '%s'..." % local_gzip_file)
        with tarfile.open(local_gzip_file, "w:gz") as tar:
            for target_config in targets_configs:
                filename = "%s_%s_%s.csv" % (target_config['slug'], sta, sto)
                local_csv_file = join(CACHE_DIR, filename)
                tar.add(local_csv_file, arcname=filename)

    if not isfile(local_gzip_file):
        abort(500, "No tarball to serve. Looked at '%s'." % local_gzip_file)

    return send_from_directory(CACHE_DIR, gzip_filename)


@app.route("/<targets>_<params>_<started_at>_<stopped_at>.nc")
def download_targets_netcdf(targets, params, started_at, stopped_at):
    """
    Grab data and orbit data for the specified `target`,
    rearrange it and return it as a NetCDF file.
    `started_at` and `stopped_at` are expected to be UTC.

    targets: string list of targets' slugs, separated by `-`.
    params: string list of targets' parameters, separated by `-`.
    """
    separator = '-'  # /!\ this char should never be in target's slugs
    targets = targets.split(separator)
    targets.sort()
    targets_configs = []
    for target in targets:
        if not target:
            abort(400, "Invalid targets format : `%s`." % targets)
        targets_configs.append(get_target_config(target))
    if 0 == len(targets_configs):
        abort(400, "No valid targets specified. What are you doing?")
    params = params.split(separator)
    params.sort()
    if 0 == len(params):
        abort(400, "No valid parameters specified. What are you doing?")
    if not is_list_in_list(params, PARAMETERS.keys()):
        abort(400, "Some parameters are not recognized in '%s'." % str(params))

    date_fmt = FILE_DATE_FMT
    try:
        started_at = datetime.datetime.strptime(started_at, date_fmt)
    except:
        abort(400, "Invalid started_at parameter : '%s'." % started_at)
    try:
        stopped_at = datetime.datetime.strptime(stopped_at, date_fmt)
    except:
        abort(400, "Invalid stopped_at parameter : '%s'." % stopped_at)
    sta = started_at.strftime(date_fmt)
    sto = stopped_at.strftime(date_fmt)

    nc_filename = "%s_%s_%s_%s.nc" % \
                  (separator.join(targets), separator.join(params), sta, sto)
    nc_path = join(CACHE_DIR, nc_filename)

    if not isfile(nc_path):
        log.debug("Creating the NetCDF file '%s'..." % nc_filename)
        nc_handle = Dataset(nc_path, "w", format="NETCDF4")
        try:
            nc_handle.description = "Model and orbit data for targets"  # todo
            nc_handle.history = "Created " + time.ctime(time.time())
            nc_handle.source = "Heliopropa (CDDP)"
            available_params = list(PROPERTIES)
            for target in targets_configs:
                target_slug = target['slug']
                log.debug("Adding group '%s' to the NetCDF..." % target_slug)
                nc_group = nc_handle.createGroup(target_slug)
                data = get_data_for_target(target, started_at, stopped_at)
                dkeys = sorted(data)
                dimension = 'dim_'+target_slug
                nc_handle.createDimension(dimension, len(dkeys))

                # TIME #
                nc_time = nc_group.createVariable('time', 'i8', (dimension,))
                nc_time.units = "hours since 1970-01-01 00:00:00"
                nc_time.calendar = "standard"
                times = []
                for dkey in dkeys:
                    time_as_string = data[dkey][0][:-6]  # remove +00:00 tail
                    date = datetime.datetime.strptime(time_as_string, date_fmt)
                    times.append(date2num(
                        date, units=nc_time.units, calendar=nc_time.calendar
                    ))
                nc_time[:] = times

                # SELECTED PARAMETERS #
                nc_vars = []
                indices = []
                for param in params:
                    indices.append(available_params.index(param))
                    nc_var = nc_group.createVariable(param, 'f8', (dimension,))
                    nc_var.units = PARAMETERS[param]['units']
                    nc_vars.append(nc_var)
                for i, nc_var in enumerate(nc_vars):
                    index = indices[i]
                    values = []
                    for dkey in dkeys:
                        dval = data[dkey]
                        values.append(dval[index])
                    nc_var[:] = values

                # ORBIT #
                nc_x = nc_group.createVariable('xhee', 'f8', (dimension,))
                nc_x.units = 'Au'
                nc_y = nc_group.createVariable('yhee', 'f8', (dimension,))
                nc_y.units = 'Au'
                values_x = []
                values_y = []
                index_x = available_params.index('xhee')
                index_y = available_params.index('yhee')
                for dkey in dkeys:
                    dval = data[dkey]
                    values_x.append(dval[index_x])
                    values_y.append(dval[index_y])
                nc_x[:] = values_x
                nc_y[:] = values_y
            log.debug("Writing NetCDF '%s'..." % nc_filename)

        except Exception as e:
            log.error("Failed to generate NetCDF '%s'." % nc_filename)
            raise e
        finally:
            nc_handle.close()

    if not isfile(nc_path):
        abort(500, "No NetCDF to serve. Looked at '%s'." % nc_path)

    return send_from_directory(CACHE_DIR, nc_filename)


@app.route("/<targets>_<started_at>_<stopped_at>.cdf")
def download_targets_cdf(targets, started_at, stopped_at):
    """
    Grab data and orbit data for the specified `target`,
    rearrange it and return it as a CDF file.
    `started_at` and `stopped_at` are expected to be UTC.

    targets: string list of targets' slugs, separated by `-`.
    params: string list of targets' parameters, separated by `-`.
    """
    separator = '-'  # /!\ this char should never be in target's slugs
    targets = targets.split(separator)
    targets.sort()
    targets_configs = []
    for target in targets:
        if not target:
            abort(400, "Invalid targets format : `%s`." % targets)
        targets_configs.append(get_target_config(target))
    if 0 == len(targets_configs):
        abort(400, "No valid targets specified. What are you doing?")

    params = PARAMETERS.keys()
    # params = params.split(separator)
    # params.sort()
    # if 0 == len(params):
    #     abort(400, "No valid parameters specified. What are you doing?")
    # if not is_list_in_list(params, PARAMETERS.keys()):
    #     abort(400, "Some parameters are not recognized in '%s'." % str(params))

    try:
        started_at = datetime.datetime.strptime(started_at, FILE_DATE_FMT)
    except:
        abort(400, "Invalid started_at parameter : '%s'." % started_at)
    try:
        stopped_at = datetime.datetime.strptime(stopped_at, FILE_DATE_FMT)
    except:
        abort(400, "Invalid stopped_at parameter : '%s'." % stopped_at)
    sta = started_at.strftime(FILE_DATE_FMT)
    sto = stopped_at.strftime(FILE_DATE_FMT)

    cdf_filename = "%s_%s_%s.cdf" % (separator.join(targets), sta, sto)
    cdf_path = join(CACHE_DIR, cdf_filename)

    if not isfile(cdf_path):
        log.debug("Creating the CDF file '%s'..." % cdf_filename)
        try:
            cdf_handle = cdf.archive()
            description = "Model and orbit data for %s." % \
                ', '.join([t['name'] for t in targets_configs])
            cdf_handle.attributes['Description'] = description
            cdf_handle.attributes['Author'] = "Heliopropa.irap.omp.eu (CDPP)"
            cdf_handle.attributes['Created'] = str(time.ctime(time.time()))

            available_params = list(PROPERTIES)
            for target in targets_configs:
                target_slug = target['slug']
                data = get_data_for_target(target, started_at, stopped_at)
                dkeys = sorted(data)

                values = []
                units = "hours since 1970-01-01 00:00:00"
                calendar = "standard"
                for dkey in dkeys:
                    time_as_string = data[dkey][0][:-6]  # remove +00:00 tail
                    date = datetime.datetime.strptime(time_as_string, FILE_DATE_FMT)
                    values.append(date2num(date, units=units, calendar=calendar))
                k = "%s_time" % target_slug
                cdf_handle[k] = values
                cdf_handle[k].attributes['units'] = units

                for param in params:
                    k = "%s_%s" % (target_slug, param)
                    values = []
                    i = available_params.index(param)
                    for dkey in dkeys:
                        values.append(data[dkey][i])
                    cdf_handle[k] = values
                    cdf_handle[k].attributes['units'] = PARAMETERS[param]['units']

                k_xhee = "%s_xhee" % target_slug
                k_yhee = "%s_yhee" % target_slug
                values_xhee = []
                values_yhee = []
                index_x = available_params.index('xhee')
                index_y = available_params.index('yhee')
                for dkey in dkeys:
                    values_xhee.append(data[dkey][index_x])
                    values_yhee.append(data[dkey][index_y])
                cdf_handle[k_xhee] = values_xhee
                cdf_handle[k_yhee] = values_yhee
                cdf_handle[k_xhee].attributes['units'] = 'Au'
                cdf_handle[k_yhee].attributes['units'] = 'Au'

            log.debug("Writing CDF '%s'..." % cdf_filename)
            cdf_handle.save(cdf_path)

        except Exception as e:
            log.error("Failed to generate CDF '%s'." % cdf_filename)
            removefile(cdf_path)
            raise

        finally:
            # cdf_handle.close()
            pass

    if not isfile(cdf_path):
        abort(500, "No CDF to serve. Looked at '%s'." % cdf_path)

    return send_from_directory(CACHE_DIR, cdf_filename)


# API #########################################################################

@app.route("/cache/clear")
def cache_clear():
    """
    Removes all files from the cache.
    Note: It also removes the .gitkeep file. Not a problem for prod.
    """
    removed_files = remove_all_files(CACHE_DIR)
    count = len(removed_files)
    return "Cache cleared! Removed %d file%s." \
           % (count, 's' if count != 1 else '')


@app.route("/cache/cleanup")
def cache_cleanup():
    """
    Removes all files from the cache that are older than roughly one month.
    Note: It also removes the .gitkeep file. Maybe it should not, but hey.
    """
    a_month_ago = datetime.datetime.now() - datetime.timedelta(days=32)
    removed_files = remove_files_created_before(a_month_ago, CACHE_DIR)
    count = len(removed_files)
    return "Cache cleaned! Removed %d old file%s." \
           % (count, 's' if count != 1 else '')


@app.route("/cache/warmup")
def cache_warmup():
    """
    Warms up the cache for the current day.
    Linked to SpaceWeather#edit in swapp.ls to get the default time interval.
    If you edit this code you'll need to edit the other as well and vice versa.
    """
    # relativedelta(years=3)
    # startted_at = datetime.datetime.now() - relativedelta(years=3)
    return "To Do"


@app.route("/log")
def log_show():
    with open(LOG_FILE, 'r') as f:
        contents = f.read()
    return contents


@app.route("/log/clear")
def log_clear():
    with open(LOG_FILE, 'w') as f:
        f.truncate()
    return "Log cleared successfully."


# DEV TOOLS ###################################################################

# @app.route("/inspect")
# def analyze_cdf():
#     """
#     For debug purposes.
#     """
#     cdf_to_inspect = get_path("../res/dummy.nc")
#     cdf_to_inspect = get_path("../res/dummy_jupiter_coordinates.nc")
#
#     si = StringIO.StringIO()
#     cw = csv.DictWriter(si, fieldnames=['Name', 'Shape', 'Length'])
#     cw.writeheader()
#
#     # Time, StartTime, StopTime, V, B, N, T, Delta_angle, P_dyn, QualityFlag
#     cdf_handle = Dataset(cdf_to_inspect, "r", format="NETCDF4")
#     for variable in cdf_handle.variables:
#         v = cdf_handle.variables[variable]
#         cw.writerow({
#             'Name': variable,
#             'Shape': v.shape,
#             'Length': v.size,
#         })
#     cdf_handle.close()
#
#     return si.getvalue()


# MAIN ########################################################################

if __name__ == "__main__":

    a = "2015171150000001"



    # Debug mode on, as the production server does not use this but run.wsgi
    extra_files = [get_path('../config.yml')]
    app.run(debug=True, extra_files=extra_files)