# -*- coding: utf-8 -*-

"""dictd C5 format writer"""

import io

import sys

import codecs

import re

import gadict

import gadict_freq

FINAME = None

FONAME = None

LANGS = None

FREQ_SOURCES = []

# -lang:ru,uk

ARG_LANG_RE = re.compile("-lang:(.+)")

# -freq:var:TAG=FILE or -freq:freq:TAG=FILE

ARG_FREQ_RE = re.compile("-freq:(freq|var):([^=]+)=(.+)")

# -grp:GLOB

ARG_GRP_RE = re.compile("-grp:(.+)")

look_for_files = False

for idx in range(1, len(sys.argv)):

    arg = sys.argv[idx]

    if arg == "--":

        look_for_files = True

        continue

    if not look_for_files:

        m = ARG_LANG_RE.match(arg)

        if m:

            LANGS = set(m.group(1).split(","))

            for lang in LANGS:

                if len(lang) != 2:

                    raise Exception("Incorrect language specification: '{:s}'".format(arg))

            continue

        m = ARG_FREQ_RE.match(arg)

        if m:

            mode = m.group(1)

            tag = m.group(2)

            fname = m.group(3)

            with io.open(fname, mode='r', buffering=1, encoding="utf-8") as stream:

                if mode == "var":

                    parser = gadict_freq.WordformParser(stream)

                elif mode == "freq":

                    parser = gadict_freq.FreqlistParser(stream)

                else:

                    raise Exception("Unsupported mode: '{:s}'".format(mode))

                wlist = parser.parse()

            FREQ_SOURCES.append((tag, set(wlist)))

            continue

        m = ARG_GRP_RE.match(arg)

        if m:

            patt = m.group(1)

            parser = gadict_freq.WordformGroupParser(patt)

            for (tag, wset) in parser.parse().items():

                FREQ_SOURCES.append((tag, wset))

            continue

        if arg.startswith("-"):

            raise Exception("Unsupported option format: '{:s}'".format(arg))

    if not FINAME:

        FINAME = arg

        continue

    if not FONAME:

        FONAME = arg

        continue

    raise Exception("Unnecessary argument: '{:s}'".format(arg))

FIN = io.open(FINAME, mode='r', buffering=1, encoding="utf-8")

PARSER = gadict.Parser()

try:

    DOM = PARSER.parse(FIN)

except gadict.ParseException as ex:

    sys.stdout.write("{:s}{:s}\n".format(FINAME, repr(ex)))

    if __debug__:

        import traceback

        traceback.print_exc()

    exit(1)

finally:

    FIN.close()

PRELUDE = DOM[0]

with open(FONAME+".name", "w") as f:        # for dictfmt -s

    if PRELUDE.name is not None:

        f.write(PRELUDE.name)

    f.write("\n")

with open(FONAME+".url", "w") as f:         # for dictfmt -u

    if len(PRELUDE.urls) > 0:

        f.write(PRELUDE.urls[0])

    f.write("\n")

if FONAME is None:

    FOUT = sys.stdout

else:

    FOUT = codecs.open(FONAME, "w", "utf-8")

if PRELUDE.name is not None:

    FOUT.write("Dictionary name: ")

    FOUT.write(PRELUDE.name)

    FOUT.write("\n\n")

FOUT.write("Project URLs: ")

FOUT.write(" , ".join(PRELUDE.urls))

FOUT.write("\n\n")

FOUT.write("Project licenses: ")

FOUT.write(", ".join(PRELUDE.licences))

FOUT.write("\n\n")

FOUT.write(PRELUDE.about)

FOUT.write("\n")

for (headwords, translations) in DOM[1:]:

    identity = headwords[0].headword

    FOUT.write("_____\n\n")

    title = "; ".join([h.headword for h in headwords])

    FOUT.write(title)

    FOUT.write("\n\n")

    for hw in headwords:

        FOUT.write(hw.headword)

        if hw.pron is not None:

            FOUT.write(" [")

            FOUT.write(hw.pron)

            FOUT.write("]")

        if len(hw.attrs) > 0:

            FOUT.write(" ")

            l = [u"«"+x+u"»" for x in hw.attrs]

            l.sort()

            FOUT.write(", ".join(l))

        if hw.homo is not None and len(hw.homo) > 0:

            FOUT.write(" homo: ")

            l = ["{"+x+"}" for x in hw.homo]

            l.sort()

            FOUT.write(", ".join(l))

        FOUT.write("\n")

    FOUT.write("\n")

    for sense in translations:

        if not sense:

            raise Exception("""Empty sense for article: """ + headwords.__iter__().__next__())

        if sense.pos:

            FOUT.write(u"● «")

            FOUT.write(sense.pos)

            FOUT.write(u"»")

            need_sep = False

            if sense.topic_list and len(sense.topic_list) > 0:

                FOUT.write(" topic: ")

                FOUT.write(", ".join(["{"+s+"}" for s in sense.topic_list]))

                need_sep = True

            if sense.ant_list and len(sense.ant_list) > 0:

                if need_sep:

                    FOUT.write(" |")

                FOUT.write(" ant: ")

                FOUT.write("; ".join(["{"+s+"}" for s in sense.ant_list]))

                need_sep = True

            if sense.syn_list and len(sense.syn_list) > 0:

                if need_sep:

                    FOUT.write(" |")

                FOUT.write(" syn: ")

                FOUT.write("; ".join(["{"+s+"}" for s in sense.syn_list]))

                need_sep = True

            if sense.hyper_list and len(sense.hyper_list) > 0:

                if need_sep:

                    FOUT.write(" |")

                FOUT.write(" hyper: ")

                FOUT.write("; ".join(["{"+s+"}" for s in sense.hyper_list]))

                need_sep = True

            if sense.hypo_list and len(sense.hypo_list) > 0:

                if need_sep:

                    FOUT.write(" |")

                FOUT.write(" hypo: ")

                FOUT.write("; ".join(["{"+s+"}" for s in sense.hypo_list]))

                need_sep = True

            if sense.col_list and len(sense.col_list) > 0:

                if need_sep:

                    FOUT.write(" |")

                FOUT.write(" col: ")

                FOUT.write("; ".join(["{"+s+"}" for s in sense.col_list]))

                need_sep = True

            if sense.rel_list and len(sense.rel_list) > 0:

                if need_sep:

                    FOUT.write(" |")

                FOUT.write(" see: ")

                FOUT.write("; ".join(["{"+s+"}" for s in sense.rel_list]))

            if not LANGS or len(LANGS) != 1:

                FOUT.write("\n")

        for (lang, tr) in sense.tr_list or []:

            if LANGS and lang not in LANGS:

                continue

            FOUT.write("  ")

            if not LANGS or len(LANGS) > 1:

                FOUT.write(lang)

                FOUT.write(u"→ ")

            FOUT.write(tr)

            FOUT.write("\n")

        for (lang, tr) in sense.glos_list or []:

            if LANGS and lang not in LANGS:

                continue

            FOUT.write("  ")

            if not LANGS or len(LANGS) > 1:

                FOUT.write(lang)

            FOUT.write(u"↦ ")

            FOUT.write(tr)

            FOUT.write("\n")

        for (lang, tr) in sense.ex_list or []:

            if LANGS and lang not in LANGS:

                continue

            FOUT.write("    ")

            if not LANGS or len(LANGS) > 1:

                FOUT.write(lang)

            FOUT.write(u"⇒ ")

            FOUT.write(tr)

            FOUT.write("\n")

    freqtags = []

    for (freqtag, freqset) in FREQ_SOURCES:

        if identity in freqset:

            freqtags.append(freqtag)

    if len(freqtags) > 0:

        FOUT.write(",".join(["{{{:s}}}".format(tag) for tag in freqtags]))

        FOUT.write("\n")