Public-Mirror/LunaTranslator
1
0
Fork 0
mirror of https://github.com/HIllya51/LunaTranslator.git synced 2024-12-28 08:04:13 +08:00
Code Issues Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
恍兮惚兮 2024-05-17 13:20:02 +08:00
parent 6f0132a166
commit 220e6e3051
20 changed files with 178 additions and 532 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

159
LunaTranslator/LunaTranslator/gui/showword.py
View File

@ -12,14 +12,14 @@ from PyQt5.QtWidgets import (
QTabWidget,
QFileDialog,
QTabBar,
QLabel,
QLabel
)
from PyQt5.QtGui import QPixmap, QImage
from traceback import print_exc
import requests, json
import requests, json, subprocess, time
from PyQt5.QtCore import pyqtSignal, Qt
import qtawesome, functools, os, base64
import gobject, uuid
import gobject, uuid, signal
from myutils.config import globalconfig, _TR, static_data
import myutils.ankiconnect as anki
from gui.usefulwidget import (
@ -31,13 +31,65 @@ from gui.usefulwidget import (
getlineedit,
getsimpleswitch,
getcolorbutton,
tabadd_lazy,
tabadd_lazy
)
from myutils.wrapper import threader
from myutils.ocrutil import imageCut, ocr_run
from gui.rangeselect import rangeselct_function
class ffmpeg_virtual_audio_capturer:
def __init__(self):
os.makedirs("./cache/tts", exist_ok=True)
self.file = os.path.abspath(
os.path.join("./cache/tts", str(time.time()) + ".mp3")
)
try:
self.engine = subprocess.Popen(
os.path.join(
globalconfig["ffmpeg"],
f'ffmpeg.exe -f dshow -i audio="virtual-audio-capturer" "{self.file}"',
),
stdin=subprocess.PIPE,
)
except:
print_exc()
def end(self):
try:
self.engine.stdin.write(b"q")
self.engine.stdin.flush()
except:
pass
class statusbutton(QPushButton):
statuschanged1 = pyqtSignal(int)
statuschanged2 = pyqtSignal(int)
def __init__(self, icons, colors):
super().__init__()
self.idx = 0
self.icons = icons
self.colors = colors
self.clicked.connect(self.setChecked)
self.seticon()
def seticon(self):
self.setIcon(
qtawesome.icon(
self.icons[(self.idx) % len(self.icons)],
color=self.colors[(self.idx) % len(self.colors)],
)
)
def setChecked(self, a0):
super().setChecked(a0)
self.idx += 1
self.statuschanged1.emit((self.idx) % len(self.icons))
self.statuschanged2.emit((self.idx) % len(self.colors))
self.seticon()
class AnkiWindow(QWidget):
__ocrsettext = pyqtSignal(str)
refreshhtml = pyqtSignal()
@ -288,8 +340,47 @@ class AnkiWindow(QWidget):
getsimpleswitch(globalconfig["ankiconnect"], "ocrcroped"),
)
layout.addWidget(QLabel())
layout.addRow(_TR("录音"), QLabel())
lb = QLabel()
lb.setOpenExternalLinks(True)
lb.setText(
'<a href="https://github.com/HIllya51/RESOURCES/releases/download/softwares/virtual-audio.zip">virtual-audio-capturer</a>'
)
layout.addRow(_TR("安装录音驱动"), lb)
ffmpegpath = getlineedit(globalconfig, "ffmpeg", readonly=True)
def selectpath():
f = QFileDialog.getExistingDirectory()
if f != "":
ffmpegpath.setText(f)
layout.addRow(
_TR("ffmpeg"),
getboxlayout(
[
ffmpegpath,
getcolorbutton(
"",
"",
selectpath,
icon="fa.gear",
constcolor="#FF69B4",
),
],
makewidget=True,
),
)
return wid
def startorendrecord(self, target: QLineEdit, idx):
if idx == 1:
self.recorder = ffmpeg_virtual_audio_capturer()
else:
self.recorder.end()
target.setText(self.recorder.file)
def createaddtab(self):
layout = QVBoxLayout()
wid = QWidget()
@ -311,6 +402,14 @@ class AnkiWindow(QWidget):
self.editpath.textChanged.connect(self.wrappedpixmap)
self.example = QPlainTextEdit()
self.remarks = QTextEdit()
recordbtn1 = statusbutton(icons=["fa.microphone", "fa.stop"], colors=[""])
recordbtn1.statuschanged1.connect(
functools.partial(self.startorendrecord, self.audiopath)
)
recordbtn2 = statusbutton(icons=["fa.microphone", "fa.stop"], colors=[""])
recordbtn2.statuschanged1.connect(
functools.partial(self.startorendrecord, self.audiopath_sentence)
)
layout.addLayout(
getboxlayout(
[
@ -335,11 +434,14 @@ class AnkiWindow(QWidget):
[
QLabel(_TR("语音")),
self.audiopath,
recordbtn1,
soundbutton,
getcolorbutton(
"",
"",
functools.partial(self.selectaudio),
functools.partial(
self.selecfile, self.audiopath
),
icon="fa.gear",
constcolor="#FF69B4",
),
@ -349,11 +451,14 @@ class AnkiWindow(QWidget):
[
QLabel(_TR("语音_例句")),
self.audiopath_sentence,
recordbtn2,
soundbutton2,
getcolorbutton(
"",
"",
functools.partial(self.selectaudio2),
functools.partial(
self.selecfile, self.audiopath_sentence
),
icon="fa.gear",
constcolor="#FF69B4",
),
@ -367,7 +472,9 @@ class AnkiWindow(QWidget):
getcolorbutton(
"",
"",
functools.partial(self.selectimage),
functools.partial(
self.selecfile, self.editpath
),
icon="fa.gear",
constcolor="#FF69B4",
),
@ -406,23 +513,11 @@ class AnkiWindow(QWidget):
pix = pix.scaled(self.viewimagelabel.size() * rate, Qt.KeepAspectRatio)
self.viewimagelabel.setPixmap(pix)
def selectimage(self):
def selecfile(self, item):
f = QFileDialog.getOpenFileName()
res = f[0]
if res != "":
self.editpath.setText(res)
def selectaudio(self):
f = QFileDialog.getOpenFileName()
res = f[0]
if res != "":
self.audiopath.setText(res)
def selectaudio2(self):
f = QFileDialog.getOpenFileName()
res = f[0]
if res != "":
self.audiopath_sentence.setText(res)
item.setText(res)
def reset(self, text):
self.currentword = text
@ -578,8 +673,8 @@ class searchwordW(closeashidewindow):
soundbutton.clicked.connect(self.langdu)
self.searchlayout.addWidget(soundbutton)
ankiconnect = QPushButton(qtawesome.icon("fa.adn"), "")
ankiconnect.clicked.connect(self.onceaddankiwindow)
ankiconnect = statusbutton(icons=["fa.adn"], colors=["", "#FF69B4"])
ankiconnect.statuschanged2.connect(self.onceaddankiwindow)
self.searchlayout.addWidget(ankiconnect)
self.tab = QTabBar(self)
@ -596,7 +691,6 @@ class searchwordW(closeashidewindow):
self.textOutput = textOutput
self.cache_results = {}
self.hiding = True
self.addankiwindowidx = 0
tablayout = QVBoxLayout()
tablayout.addWidget(self.tab)
@ -604,16 +698,17 @@ class searchwordW(closeashidewindow):
tablayout.setContentsMargins(0, 0, 0, 0)
tablayout.setSpacing(0)
self.vboxlayout.addLayout(tablayout)
self.isfirstshowanki = True
def onceaddankiwindow(self):
if self.addankiwindowidx == 0:
self.vboxlayout.addWidget(self.ankiwindow)
else:
if self.addankiwindowidx % 2 == 0:
self.ankiwindow.show()
def onceaddankiwindow(self, idx):
if idx == 1:
if self.isfirstshowanki:
self.vboxlayout.addWidget(self.ankiwindow)
else:
self.ankiwindow.hide()
self.addankiwindowidx += 1
self.ankiwindow.show()
else:
self.ankiwindow.hide()
self.isfirstshowanki = False
def langdu(self):
if gobject.baseobject.reader:

3
LunaTranslator/LunaTranslator/gui/usefulwidget.py
View File

@ -399,9 +399,10 @@ def getsimplecombobox(lst, d, k, callback=None):
return s
def getlineedit(d, key, callback=None):
def getlineedit(d, key, callback=None, readonly=False):
s = QLineEdit()
s.setText(d[key])
s.setReadOnly(readonly)
s.textChanged.connect(functools.partial(callbackwrap, d, key, callback))
return s

485
LunaTranslator/LunaTranslator/tts/gtts.py
View File

@ -84,22 +84,6 @@ log.addHandler(logging.NullHandler())
def tts_langs():
"""Languages Google Text-to-Speech supports.
Returns:
dict: A dictionary of the type `{ '<lang>': '<name>'}`
Where `<lang>` is an IETF language tag such as `en` or `zh-TW`,
and `<name>` is the full English name of the language, such as
`English` or `Chinese (Mandarin/Taiwan)`.
The dictionary returned combines languages from two origins:
- Languages fetched from Google Translate (pre-generated in :mod:`gtts.langs`)
- Languages that are undocumented variations that were observed to work and
present different dialects or accents.
"""
langs = dict()
langs.update(_main_langs())
langs.update(_extra_langs())
@ -108,16 +92,6 @@ def tts_langs():
def _extra_langs():
"""Define extra languages.
Returns:
dict: A dictionary of extra languages manually defined.
Variations of the ones generated in `_main_langs`,
observed to provide different dialects or accents or
just simply accepted by the Google Translate Text-to-Speech API.
"""
return {
# Chinese
"zh-TW": "Chinese (Mandarin/Taiwan)",
@ -126,25 +100,6 @@ def _extra_langs():
def _fallback_deprecated_lang(lang):
"""Languages Google Text-to-Speech used to support.
Language tags that don't work anymore, but that can
fallback to a more general language code to maintain
compatibility.
Args:
lang (string): The language tag.
Returns:
string: The language tag, as-is if not deprecated,
or a fallback if it exits.
Example:
``en-GB`` returns ``en``.
``en-gb`` returns ``en``.
"""
deprecated = {
# '<fallback>': [<list of deprecated langs>]
"en": [
@ -205,51 +160,6 @@ class symbols:
class RegexBuilder:
r"""Builds regex using arguments passed into a pattern template.
Builds a regex object for which the pattern is made from an argument
passed into a template. If more than one argument is passed (iterable),
each pattern is joined by "|" (regex alternation 'or') to create a
single pattern.
Args:
pattern_args (iteratable): String element(s) to be each passed to
``pattern_func`` to create a regex pattern. Each element is
``re.escape``'d before being passed.
pattern_func (callable): A 'template' function that should take a
string and return a string. It should take an element of
``pattern_args`` and return a valid regex pattern group string.
flags: ``re`` flag(s) to compile with the regex.
Example:
To create a simple regex that matches on the characters "a", "b",
or "c", followed by a period::
>>> rb = RegexBuilder('abc', lambda x: "{}\.".format(x))
Looking at ``rb.regex`` we get the following compiled regex::
>>> print(rb.regex)
'a\.|b\.|c\.'
The above is fairly simple, but this class can help in writing more
complex repetitive regex, making them more readable and easier to
create by using existing data structures.
Example:
To match the character following the words "lorem", "ipsum", "meili"
or "koda"::
>>> words = ['lorem', 'ipsum', 'meili', 'koda']
>>> rb = RegexBuilder(words, lambda x: "(?<={}).".format(x))
Looking at ``rb.regex`` we get the following compiled regex::
>>> print(rb.regex)
'(?<=lorem).|(?<=ipsum).|(?<=meili).|(?<=koda).'
"""
def __init__(self, pattern_args, pattern_func, flags=0):
self.pattern_args = pattern_args
self.pattern_func = pattern_func
@ -273,49 +183,6 @@ class RegexBuilder:
class PreProcessorRegex:
r"""Regex-based substitution text pre-processor.
Runs a series of regex substitutions (``re.sub``) from each ``regex`` of a
:class:`gtts.tokenizer.core.RegexBuilder` with an extra ``repl``
replacement parameter.
Args:
search_args (iteratable): String element(s) to be each passed to
``search_func`` to create a regex pattern. Each element is
``re.escape``'d before being passed.
search_func (callable): A 'template' function that should take a
string and return a string. It should take an element of
``search_args`` and return a valid regex search pattern string.
repl (string): The common replacement passed to the ``sub`` method for
each ``regex``. Can be a raw string (the case of a regex
backreference, for example)
flags: ``re`` flag(s) to compile with each `regex`.
Example:
Add "!" after the words "lorem" or "ipsum", while ignoring case::
>>> import re
>>> words = ['lorem', 'ipsum']
>>> pp = PreProcessorRegex(words,
... lambda x: "({})".format(x), r'\\1!',
... re.IGNORECASE)
In this case, the regex is a group and the replacement uses its
backreference ``\\1`` (as a raw string). Looking at ``pp`` we get the
following list of search/replacement pairs::
>>> print(pp)
(re.compile('(lorem)', re.IGNORECASE), repl='\1!'),
(re.compile('(ipsum)', re.IGNORECASE), repl='\1!')
It can then be run on any string of text::
>>> pp.run("LOREM ipSuM")
"LOREM! ipSuM!"
See :mod:`gtts.tokenizer.pre_processors` for more examples.
"""
def __init__(self, search_args, search_func, repl, flags=0):
self.repl = repl
@ -327,16 +194,6 @@ class PreProcessorRegex:
self.regexes.append(rb.regex)
def run(self, text):
"""Run each regex substitution on ``text``.
Args:
text (string): the input text.
Returns:
string: text after all substitutions have been sequentially
applied.
"""
for regex in self.regexes:
text = regex.sub(self.repl, text)
return text
@ -349,39 +206,6 @@ class PreProcessorRegex:
class PreProcessorSub:
r"""Simple substitution text preprocessor.
Performs string-for-string substitution from list a find/replace pairs.
It abstracts :class:`gtts.tokenizer.core.PreProcessorRegex` with a default
simple substitution regex.
Args:
sub_pairs (list): A list of tuples of the style
``(<search str>, <replace str>)``
ignore_case (bool): Ignore case during search. Defaults to ``True``.
Example:
Replace all occurences of "Mac" to "PC" and "Firefox" to "Chrome"::
>>> sub_pairs = [('Mac', 'PC'), ('Firefox', 'Chrome')]
>>> pp = PreProcessorSub(sub_pairs)
Looking at the ``pp``, we get the following list of
search (regex)/replacement pairs::
>>> print(pp)
(re.compile('Mac', re.IGNORECASE), repl='PC'),
(re.compile('Firefox', re.IGNORECASE), repl='Chrome')
It can then be run on any string of text::
>>> pp.run("I use firefox on my mac")
"I use Chrome on my PC"
See :mod:`gtts.tokenizer.pre_processors` for more examples.
"""
def __init__(self, sub_pairs, ignore_case=True):
def search_func(x):
return "{}".format(x)
@ -396,16 +220,6 @@ class PreProcessorSub:
self.pre_processors.append(pp)
def run(self, text):
"""Run each substitution on ``text``.
Args:
text (string): the input text.
Returns:
string: text after all substitutions have been sequentially
applied.
"""
for pp in self.pre_processors:
text = pp.run(text)
return text
@ -415,80 +229,6 @@ class PreProcessorSub:
class Tokenizer:
r"""An extensible but simple generic rule-based tokenizer.
A generic and simple string tokenizer that takes a list of functions
(called `tokenizer cases`) returning ``regex`` objects and joins them by
"|" (regex alternation 'or') to create a single regex to use with the
standard ``regex.split()`` function.
``regex_funcs`` is a list of any function that can return a ``regex``
(from ``re.compile()``) object, such as a
:class:`gtts.tokenizer.core.RegexBuilder` instance (and its ``regex``
attribute).
See the :mod:`gtts.tokenizer.tokenizer_cases` module for examples.
Args:
regex_funcs (list): List of compiled ``regex`` objects. Each
function's pattern will be joined into a single pattern and
compiled.
flags: ``re`` flag(s) to compile with the final regex. Defaults to
``re.IGNORECASE``
Note:
When the ``regex`` objects obtained from ``regex_funcs`` are joined,
their individual ``re`` flags are ignored in favour of ``flags``.
Raises:
TypeError: When an element of ``regex_funcs`` is not a function, or
a function that does not return a compiled ``regex`` object.
Warning:
Joined ``regex`` patterns can easily interfere with one another in
unexpected ways. It is recommanded that each tokenizer case operate
on distinct or non-overlapping chracters/sets of characters
(For example, a tokenizer case for the period (".") should also
handle not matching/cutting on decimals, instead of making that
a seperate tokenizer case).
Example:
A tokenizer with a two simple case (*Note: these are bad cases to
tokenize on, this is simply a usage example*)::
>>> import re, RegexBuilder
>>>
>>> def case1():
... return re.compile("\,")
>>>
>>> def case2():
... return RegexBuilder('abc', lambda x: "{}\.".format(x)).regex
>>>
>>> t = Tokenizer([case1, case2])
Looking at ``case1().pattern``, we get::
>>> print(case1().pattern)
'\\,'
Looking at ``case2().pattern``, we get::
>>> print(case2().pattern)
'a\\.|b\\.|c\\.'
Finally, looking at ``t``, we get them combined::
>>> print(t)
're.compile('\\,|a\\.|b\\.|c\\.', re.IGNORECASE)
from: [<function case1 at 0x10bbcdd08>, <function case2 at 0x10b5c5e18>]'
It can then be run on any string of text::
>>> t.run("Hello, my name is Linda a. Call me Lin, b. I'm your friend")
['Hello', ' my name is Linda ', ' Call me Lin', ' ', " I'm your friend"]
"""
def __init__(self, regex_funcs, flags=re.IGNORECASE):
self.regex_funcs = regex_funcs
self.flags = flags
@ -511,15 +251,6 @@ class Tokenizer:
return re.compile(pattern, self.flags)
def run(self, text):
"""Tokenize `text`.
Args:
text (string): the input text to tokenize.
Returns:
list: A list of strings (token) split according to the tokenizer cases.
"""
return self.total_regex.split(text)
def __repr__(self): # pragma: no cover
@ -529,51 +260,22 @@ class Tokenizer:
class tokenizer_cases:
def tone_marks():
"""Keep tone-modifying punctuation by matching following character.
Assumes the `tone_marks` pre-processor was run for cases where there might
not be any space after a tone-modifying punctuation mark.
"""
return RegexBuilder(
pattern_args=symbols.TONE_MARKS, pattern_func=lambda x: "(?<={}).".format(x)
).regex
def period_comma():
"""Period and comma case.
Match if not preceded by ".<letter>" and only if followed by space.
Won't cut in the middle/after dotted abbreviations; won't cut numbers.
Note:
Won't match if a dotted abbreviation ends a sentence.
Note:
Won't match the end of a sentence if not followed by a space.
"""
return RegexBuilder(
pattern_args=symbols.PERIOD_COMMA,
pattern_func=lambda x: r"(?<!\.[a-z]){} ".format(x),
).regex
def colon():
"""Colon case.
Match a colon ":" only if not preceded by a digit.
Mainly to prevent a cut in the middle of time notations e.g. 10:01
"""
return RegexBuilder(
pattern_args=symbols.COLON, pattern_func=lambda x: r"(?<!\d){}".format(x)
).regex
def other_punctuation():
"""Match other punctuation.
Match other punctuation to split on; punctuation that naturally
inserts a break in speech.
"""
punc = "".join(
set(symbols.ALL_PUNC)
- set(symbols.TONE_MARKS)
@ -584,11 +286,7 @@ class tokenizer_cases:
pattern_args=punc, pattern_func=lambda x: "{}".format(x)
).regex
def legacy_all_punctuation(): # pragma: no cover b/c tested but Coveralls: ¯\_(ツ)_/¯
"""Match all punctuation.
Use as only tokenizer case to mimic gTTS 1.x tokenization.
"""
def legacy_all_punctuation():
punc = symbols.ALL_PUNC
return RegexBuilder(
pattern_args=punc, pattern_func=lambda x: "{}".format(x)
@ -598,12 +296,6 @@ class tokenizer_cases:
class pre_processors:
def tone_marks(text):
"""Add a space after tone-modifying punctuation.
Because the `tone_marks` tokenizer case will split after a tone-modifying
punctuation mark, make sure there's whitespace after.
"""
return PreProcessorRegex(
search_args=symbols.TONE_MARKS,
search_func=lambda x: "(?<={})".format(x),
@ -611,29 +303,11 @@ class pre_processors:
).run(text)
def end_of_line(text):
"""Re-form words cut by end-of-line hyphens.
Remove "<hyphen><newline>".
"""
return PreProcessorRegex(
search_args="-", search_func=lambda x: "{}\n".format(x), repl=""
).run(text)
def abbreviations(text):
"""Remove periods after an abbreviation from a list of known
abbreviations that can be spoken the same without that period. This
prevents having to handle tokenization of that period.
Note:
Could potentially remove the ending period of a sentence.
Note:
Abbreviations that Google Translate can't pronounce without
(or even with) a period should be added as a word substitution with a
:class:`PreProcessorSub` pre-processor. Ex.: 'Esq.', 'Esquire'.
"""
return PreProcessorRegex(
search_args=symbols.ABBREVIATIONS,
search_func=lambda x: r"(?<={})(?=\.).".format(x),
@ -642,7 +316,6 @@ class pre_processors:
).run(text)
def word_sub(text):
"""Word-for-word substitutions."""
return PreProcessorSub(sub_pairs=symbols.SUB_PAIRS).run(text)
@ -651,37 +324,8 @@ from string import whitespace as ws
import re
_ALL_PUNC_OR_SPACE = re.compile("^[{}]*$".format(re.escape(punc + ws)))
"""Regex that matches if an entire line is only comprised
of whitespace and punctuation
"""
def _minimize(the_string, delim, max_size):
"""Recursively split a string in the largest chunks
possible from the highest position of a delimiter all the way
to a maximum size
Args:
the_string (string): The string to split.
delim (string): The delimiter to split on.
max_size (int): The maximum size of a chunk.
Returns:
list: the minimized string in tokens
Every chunk size will be at minimum ``the_string[0:idx]`` where ``idx``
is the highest index of ``delim`` found in ``the_string``; and at maximum
``the_string[0:max_size]`` if no ``delim`` was found in ``the_string``.
In the latter case, the split will occur at ``the_string[max_size]``
which can be any character. The function runs itself again on the rest of
``the_string`` (``the_string[idx:]``) until no chunk is larger than
``max_size``.
"""
# Remove `delim` from start of `the_string`
# i.e. prevent a recursive infinite loop on `the_string[0:0]`
# if `the_string` starts with `delim` and is larger than `max_size`
if the_string.startswith(delim):
the_string = the_string[len(delim) :]
@ -701,31 +345,10 @@ def _minimize(the_string, delim, max_size):
def _clean_tokens(tokens):
"""Clean a list of strings
Args:
tokens (list): A list of strings (tokens) to clean.
Returns:
list: Stripped strings ``tokens`` without the original elements
that only consisted of whitespace and/or punctuation characters.
"""
return [t.strip() for t in tokens if not _ALL_PUNC_OR_SPACE.match(t)]
def _translate_url(tld="com", path=""):
"""Generates a Google Translate URL
Args:
tld (string): Top-level domain for the Google Translate host,
i.e ``https://translate.google.<tld>``. Default is ``com``.
path: (string): A path to append to the Google Translate host,
i.e ``https://translate.google.com/<path>``. Default is ``""``.
Returns:
string: A Google Translate URL `https://translate.google.<tld>/path`
"""
_GOOGLE_TTS_URL = "https://translate.google.{}/{}"
return _GOOGLE_TTS_URL.format(tld, path)
@ -738,76 +361,11 @@ log.addHandler(logging.NullHandler())
class Speed:
"""Read Speed
The Google TTS Translate API supports two speeds:
Slow: True
Normal: None
"""
SLOW = True
NORMAL = None
class gTTS:
"""gTTS -- Google Text-to-Speech.
An interface to Google Translate's Text-to-Speech API.
Args:
text (string): The text to be read.
tld (string): Top-level domain for the Google Translate host,
i.e `https://translate.google.<tld>`. Different Google domains
can produce different localized 'accents' for a given
language. This is also useful when ``google.com`` might be blocked
within a network but a local or different Google host
(e.g. ``google.com.hk``) is not. Default is ``com``.
lang (string, optional): The language (IETF language tag) to
read the text in. Default is ``en``.
slow (bool, optional): Reads text more slowly. Defaults to ``False``.
lang_check (bool, optional): Strictly enforce an existing ``lang``,
to catch a language error early. If set to ``True``,
a ``ValueError`` is raised if ``lang`` doesn't exist.
Setting ``lang_check`` to ``False`` skips Web requests
(to validate language) and therefore speeds up instantiation.
Default is ``True``.
pre_processor_funcs (list): A list of zero or more functions that are
called to transform (pre-process) text before tokenizing. Those
functions must take a string and return a string. Defaults to::
[
pre_processors.tone_marks,
pre_processors.end_of_line,
pre_processors.abbreviations,
pre_processors.word_sub
]
tokenizer_func (callable): A function that takes in a string and
returns a list of string (tokens). Defaults to::
Tokenizer([
tokenizer_cases.tone_marks,
tokenizer_cases.period_comma,
tokenizer_cases.colon,
tokenizer_cases.other_punctuation
]).run
timeout (float or tuple, optional): Seconds to wait for the server to
send data before giving up, as a float, or a ``(connect timeout,
read timeout)`` tuple. ``None`` will wait forever (default).
See Also:
:doc:`Pre-processing and tokenizing <tokenizer>`
Raises:
AssertionError: When ``text`` is ``None`` or empty; when there's nothing
left to speak after pre-precessing, tokenizing and cleaning.
ValueError: When ``lang_check`` is ``True`` and ``lang`` is not supported.
RuntimeError: When ``lang_check`` is ``True`` but there's an error loading
the languages dictionary.
"""
GOOGLE_TTS_MAX_CHARS = 100 # Max characters the Google TTS API takes at a time
GOOGLE_TTS_HEADERS = {
"Referer": "http://translate.google.com/",
@ -913,12 +471,6 @@ class gTTS:
return tokens
def _prepare_requests(self):
"""Created the TTS API the request(s) without sending them.
Returns:
list: ``requests.PreparedRequests_``. <https://2.python-requests.org/en/master/api/#requests.PreparedRequest>`_``.
"""
# TTS API URL
translate_url = _translate_url(
tld=self.tld, path="_/TranslateWebserverUi/data/batchexecute"
)
@ -956,14 +508,6 @@ class gTTS:
return "f.req={}&".format(urllib.parse.quote(espaced_rpc))
def stream(self):
"""Do the TTS API request(s) and stream bytes
Raises:
:class:`gTTSError`: When there's an error with the API request.
"""
# When disabling ssl verify in requests (for proxies and firewalls),
# urllib3 prints an insecure warning on stdout. We disable that.
try:
requests.packages.urllib3.disable_warnings(
requests.packages.urllib3.exceptions.InsecureRequestWarning
@ -989,16 +533,6 @@ class gTTS:
log.debug("part-%i created", idx)
def write_to_fp(self, fp):
"""Do the TTS API request(s) and write bytes to a file-like object.
Args:
fp (file object): Any file-like object to write the ``mp3`` to.
Raises:
:class:`gTTSError`: When there's an error with the API request.
TypeError: When ``fp`` is not a file-like object that takes bytes.
"""
try:
for idx, decoded in enumerate(self.stream()):
@ -1010,15 +544,6 @@ class gTTS:
)
def save(self, savefile):
"""Do the TTS API request and write result to file.
Args:
savefile (string): The path and file name to save the ``mp3`` to.
Raises:
:class:`gTTSError`: When there's an error with the API request.
"""
with open(str(savefile), "wb") as f:
self.write_to_fp(f)
f.flush()
@ -1026,8 +551,6 @@ class gTTS:
class gTTSError(Exception):
"""Exception that uses context to present a meaningful error message"""
def __init__(self, msg=None, **kwargs):
self.tts = kwargs.pop("tts", None)
self.rsp = kwargs.pop("response", None)
@ -1040,10 +563,6 @@ class gTTSError(Exception):
super(gTTSError, self).__init__(self.msg)
def infer_msg(self, tts, rsp=None):
"""Attempt to guess what went wrong by using known
information (e.g. http response) and observed behaviour
"""
cause = "Unknown"
if rsp is None:
@ -1077,7 +596,7 @@ class gTTSError(Exception):
from tts.basettsclass import TTSbase
from myutils.config import globalconfig, getlangsrc
from myutils.config import getlangsrc
class TTS(TTSbase):

1
LunaTranslator/files/defaultconfig/config.json
View File

@ -54,6 +54,7 @@
"changecharset": false,
"changecharset_charset": 2
},
"ffmpeg": "",
"requestinterval": 1,
"keepontop": true,
"buttonsize": 20,

4
LunaTranslator/files/lang/ar.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "تحديث القالب عند إضافة",
"截图后进行OCR": "التعرف الضوئي على الحروف",
"优先级": "الأولوية",
"编码": "ترميز"
"编码": "ترميز",
"安装录音驱动": "تثبيت برنامج تشغيل التسجيل",
"录音": "تسجيل صوتي"
}

4
LunaTranslator/files/lang/cht.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "添加時更新範本",
"截图后进行OCR": "截圖後進行OCR",
"优先级": "優先順序",
"编码": "編碼"
"编码": "編碼",
"安装录音驱动": "安裝錄音驅動",
"录音": "錄音"
}

4
LunaTranslator/files/lang/en.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Update template when adding",
"截图后进行OCR": "Perform OCR after taking screenshots",
"优先级": "priority",
"编码": "coding"
"编码": "coding",
"安装录音驱动": "Install recording driver",
"录音": "tape"
}

4
LunaTranslator/files/lang/es.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Actualizar la plantilla al agregar",
"截图后进行OCR": "OCR después de la captura de pantalla",
"优先级": "Prioridad",
"编码": "Codificación"
"编码": "Codificación",
"安装录音驱动": "Instalación de la unidad de grabación",
"录音": "Grabación"
}

4
LunaTranslator/files/lang/fr.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Mettre à jour le modèle lorsque vous l'ajoutez",
"截图后进行OCR": "OCR après capture d'écran",
"优先级": "Priorité",
"编码": "Codage"
"编码": "Codage",
"安装录音驱动": "Installer le driver d'enregistrement",
"录音": "Enregistrement sonore"
}

4
LunaTranslator/files/lang/it.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Aggiorna modello quando aggiungi",
"截图后进行OCR": "Esegui OCR dopo aver scattato screenshot",
"优先级": "priorità",
"编码": "codifica"
"编码": "codifica",
"安装录音驱动": "Installa il driver di registrazione",
"录音": "nastro"
}

4
LunaTranslator/files/lang/ja.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "追加時にテンプレートを更新する",
"截图后进行OCR": "スクリーンショット後にOCR",
"优先级": "優先度",
"编码": "エンコード"
"编码": "エンコード",
"安装录音驱动": "録音ドライブのインストール",
"录音": "レコーディング"
}

4
LunaTranslator/files/lang/ko.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "추가 시 템플릿 업데이트",
"截图后进行OCR": "캡처해서 OCR 진행하도록 하겠습니다.",
"优先级": "우선 순위",
"编码": "인코딩"
"编码": "인코딩",
"安装录音驱动": "녹음 드라이브 설치",
"录音": "녹음"
}

4
LunaTranslator/files/lang/pl.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Aktualizuj szablon podczas dodawania",
"截图后进行OCR": "Wykonanie OCR po wykonaniu zrzutów ekranu",
"优先级": "priorytet",
"编码": "kodowanie"
"编码": "kodowanie",
"安装录音驱动": "Zainstaluj sterownik nagrywania",
"录音": "taśma"
}

4
LunaTranslator/files/lang/ru.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Обновить шаблон при добавлении",
"截图后进行OCR": "Снимок экрана после OCR",
"优先级": "Приоритеты",
"编码": "Код"
"编码": "Код",
"安装录音驱动": "Установка привода звукозаписи",
"录音": "Запись"
}

4
LunaTranslator/files/lang/th.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "ปรับปรุงแม่แบบเมื่อคุณเพิ่ม",
"截图后进行OCR": "ทำ OCR หลังจากจับภาพหน้าจอ",
"优先级": "ลำดับความสำคัญ",
"编码": "การเข้ารหัส"
"编码": "การเข้ารหัส",
"安装录音驱动": "ติดตั้งไดรฟ์บันทึก",
"录音": "การบันทึกเสียง"
}

4
LunaTranslator/files/lang/tr.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Eklence şablonu güncelle",
"截图后进行OCR": "Ekran fotoğraflarını aldıktan sonra OCR yap",
"优先级": "Prioritet",
"编码": "coding"
"编码": "coding",
"安装录音驱动": "Kayıt sürücüsünü kur",
"录音": "kaset"
}

4
LunaTranslator/files/lang/uk.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Оновити шаблон під час додавання",
"截图后进行OCR": "Виконати OCR після роботи знімків екрана",
"优先级": "пріоритет",
"编码": "кодування"
"编码": "кодування",
"安装录音驱动": "Встановити драйвер запису",
"录音": "стрічку"
}

4
LunaTranslator/files/lang/vi.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "Cập nhật mẫu khi thêm",
"截图后进行OCR": "OCR sau khi chụp ảnh màn hình",
"优先级": "Ưu tiên",
"编码": "Mã hóa"
"编码": "Mã hóa",
"安装录音驱动": "Cài đặt Recording Drive",
"录音": "Ghi âm"
}

4
LunaTranslator/files/lang/zh.json
View File

@ -788,5 +788,7 @@
"添加时更新模板": "",
"截图后进行OCR": "",
"优先级": "",
"编码": ""
"编码": "",
"安装录音驱动": "",
"录音": ""
}

2
plugins/CMakeLists.txt
View File

@ -29,7 +29,7 @@ include(generate_product_version)
set(VERSION_MAJOR 2)
set(VERSION_MINOR 51)
set(VERSION_PATCH 2)
set(VERSION_PATCH 3)
add_library(pch pch.cpp)
target_precompile_headers(pch PUBLIC pch.h)