chgksuite 0.26.0b9__tar.gz → 0.26.0b11__tar.gz

{chgksuite-0.26.0b9/chgksuite.egg-info → chgksuite-0.26.0b11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chgksuite
-Version: 0.26.0b9
+Version: 0.26.0b11
 Summary: A package for chgk automation
 Home-page: https://gitlab.com/peczony/chgksuite
 Author: Alexander Pecheny

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/cli.py

@@ -72,37 +72,6 @@ class ArgparseBuilder:
             advanced=True,
             argtype="filename",
         )
-        self.add_argument(
-            parser,
-            "--add_ts",
-            "-ts",
-            choices=["on", "off"],
-            default=default_overrides.get("add_ts") or "off",
-            help="append timestamp to filenames",
-            caption="Добавить временную отметку в имя файла",
-            advanced=True,
-            argtype="radiobutton",
-        )
-        self.add_argument(
-            parser,
-            "--replace_no_break_spaces",
-            choices=["on", "off"],
-            default=default_overrides.get("replace_no_break_spaces") or "on",
-            help="add non-breaking spaces where applicable",
-            caption="Добавить неразрывные пробелы",
-            advanced=True,
-            argtype="radiobutton",
-        )
-        self.add_argument(
-            parser,
-            "--replace_no_break_hyphens",
-            choices=["on", "off"],
-            default=default_overrides.get("replace_no_break_hyphens") or "on",
-            help="add non-breaking hyphens where applicable",
-            caption="Добавить неразрывные дефисы",
-            advanced=True,
-            argtype="radiobutton",
-        )
         self.add_argument(
             parser,
             "-v",
@@ -298,6 +267,47 @@ class ArgparseBuilder:
             caption="Обработка строчек, состоящих из одного числа",
             argtype="radiobutton",
         )
+        self.add_argument(
+            cmdparse,
+            "--tour_numbers_as_words",
+            choices=["on", "off"],
+            default=default_overrides.get("tour_numbers_as_words") or "off",
+            help="force tour numbers as words",
+            caption="Номера туров словами",
+            advanced=True,
+            argtype="radiobutton",
+        )
+        self.add_argument(
+            cmdparse,
+            "--add_ts",
+            "-ts",
+            choices=["on", "off"],
+            default=default_overrides.get("add_ts") or "off",
+            help="append timestamp to filenames",
+            caption="Добавить временную отметку в имя файла",
+            advanced=True,
+            argtype="radiobutton",
+        )
+        self.add_argument(
+            cmdparse,
+            "--replace_no_break_spaces",
+            choices=["on", "off"],
+            default=default_overrides.get("replace_no_break_spaces") or "on",
+            help="add non-breaking spaces where applicable",
+            caption="Добавить неразрывные пробелы",
+            advanced=True,
+            argtype="radiobutton",
+        )
+        self.add_argument(
+            cmdparse,
+            "--replace_no_break_hyphens",
+            choices=["on", "off"],
+            default=default_overrides.get("replace_no_break_hyphens") or "on",
+            help="add non-breaking hyphens where applicable",
+            caption="Добавить неразрывные дефисы",
+            advanced=True,
+            argtype="radiobutton",
+        )
 
         cmdcompose = subparsers.add_parser("compose")
         self.add_argument(
@@ -334,6 +344,37 @@ class ArgparseBuilder:
             caption="Client ID для API Imgur",
             advanced=True,
         )
+        self.add_argument(
+            cmdcompose,
+            "--add_ts",
+            "-ts",
+            choices=["on", "off"],
+            default=default_overrides.get("add_ts") or "off",
+            help="append timestamp to filenames",
+            caption="Добавить временную отметку в имя файла",
+            advanced=True,
+            argtype="radiobutton",
+        )
+        self.add_argument(
+            cmdcompose,
+            "--replace_no_break_spaces",
+            choices=["on", "off"],
+            default=default_overrides.get("replace_no_break_spaces") or "on",
+            help="add non-breaking spaces where applicable",
+            caption="Добавить неразрывные пробелы",
+            advanced=True,
+            argtype="radiobutton",
+        )
+        self.add_argument(
+            cmdcompose,
+            "--replace_no_break_hyphens",
+            choices=["on", "off"],
+            default=default_overrides.get("replace_no_break_hyphens") or "on",
+            help="add non-breaking hyphens where applicable",
+            caption="Добавить неразрывные дефисы",
+            advanced=True,
+            argtype="radiobutton",
+        )
         cmdcompose_filetype = cmdcompose.add_subparsers(dest="filetype")
         cmdcompose_docx = cmdcompose_filetype.add_parser("docx")
         self.add_argument(

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/composer/pptx.py

@@ -182,9 +182,8 @@ class PptxExporter(BaseExporter):
             r = self.add_run(
                 p,
                 self._replace_no_break(
-                    ("\n" if add_line_break else "")
+                    ("\n\n" if add_line_break else "")
                     + self.pptx_process_text(editor[0][1])
-                    + "\n"
                 ),
             )
             add_line_break = True
@@ -193,9 +192,8 @@ class PptxExporter(BaseExporter):
                 r = self.add_run(
                     p,
                     self._replace_no_break(
-                        ("\n" if add_line_break else "")
+                        ("\n\n" if add_line_break else "")
                         + self.pptx_process_text(element[1])
-                        + "\n"
                     ),
                 )
                 add_line_break = True

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/parser.py

@@ -91,6 +91,19 @@ class ChgkParser:
     BADNEXTFIELDS = set(["question", "answer"])
     RE_NUM = re.compile("^([0-9]+)\\.?$")
     RE_NUM_START = re.compile("^([0-9]+)\\.")
+    ZERO_PREFIXES = ("Нулевой вопрос", "Разминочный вопрос")
+    TOUR_NUMBERS_AS_WORDS = (
+        "Первый",
+        "Второй",
+        "Третий",
+        "Четвертый",
+        "Пятый",
+        "Шестой",
+        "Седьмой",
+        "Восьмой",
+        "Девятый",
+        "Десятый",
+    )
 
     def __init__(self, defaultauthor=None, args=None, logger=None):
         self.defaultauthor = defaultauthor
@@ -200,7 +213,7 @@ class ChgkParser:
     @classmethod
     def _replace(cls, obj, val, new_val):
         if isinstance(obj, str):
-            return obj.replace(val, new_val)
+            return obj.replace(val, new_val).strip()
         elif isinstance(obj, list):
             for i, el in enumerate(obj):
                 obj[i] = cls._replace(el, val, new_val)
@@ -214,6 +227,11 @@ class ChgkParser:
             for el in val:
                 self._get_strings(el, list_)
 
+    def _get_strings_joined(self, val):
+        strings = []
+        self._get_strings(val, strings)
+        return "\n".join(strings)
+
     def _try_extract_field(self, question, k):
         regex = self.regexes[k]
         keys = sorted(question.keys())
@@ -255,14 +273,18 @@ class ChgkParser:
             and not question["number"].strip()
         ):
             question.pop("number")
+        question_str = self._get_strings_joined(question["question"])
+        for prefix in self.ZERO_PREFIXES:
+            if question_str.startswith(prefix):
+                question["question"] = self._replace(question["question"], prefix, "")
+                question["number"] = 0
+                question_str = self._get_strings_joined(question["question"])
         for k in ("zachet", "nezachet", "source", "comment", "author"):
             if k not in question:
                 self._try_extract_field(question, k)
-        strings = []
-        self._get_strings(question["question"], strings)
-        strings = "\n".join(strings)
+        question_str = self._get_strings_joined(question["question"])
         handout = self.labels["question_labels"]["handout"]
-        srch = re.search(f"{handout}:([ \n]+)\\[", strings, flags=re.DOTALL)
+        srch = re.search(f"{handout}:([ \n]+)\\[", question_str, flags=re.DOTALL)
         if srch:
             question["question"] = self._replace(
                 question["question"],
@@ -502,17 +524,30 @@ class ChgkParser:
                 if element[0] == "question":
                     try:
                         num = regexes["question"].search(element[1])
-                        if num:
-                            self.structure.insert(_id, ["number", num.group(1)])
+                        if num and num.group("number"):
+                            self.structure.insert(_id, ["number", num.group("number")])
                     except Exception as e:
                         sys.stderr.write(
                             f"exception at line 445 of parser: {type(e)} {e}\n"
                         )
-                # TODO: переделать корявую обработку авторки на нормальную
-                before_replacement = element[1]
-                element[1] = regexes[element[0]].sub("", element[1], 1)
+                    if (
+                        not num
+                        and ("нулевой вопрос" in element[1].lower())
+                        or ("разминочный вопрос" in element[1].lower())
+                    ):
+                        self.structure.insert(_id, ["number", "0"])
+                if element[0] == "question":
+                    lines = element[1].split(SEP)
+                    for i, line in enumerate(lines):
+                        if regexes["question"].search(line):
+                            lines[i] = regexes["question"].sub("", line, 1)
+                    element[1] = SEP.join([x.strip() for x in lines if x.strip()])
+                else:
+                    before_replacement = element[1]
+                    element[1] = regexes[element[0]].sub("", element[1], 1)
                 if element[1].startswith(SEP):
                     element[1] = element[1][len(SEP) :]
+                # TODO: переделать корявую обработку авторки на нормальную
                 if element[0] == "author" and "авторка:" in before_replacement.lower():
                     element[1] = "!!Авторка" + element[1]
 
@@ -529,7 +564,7 @@ class ChgkParser:
                 try:
                     num = regexes["question"].search(element[1])
                     if num:
-                        self.structure.insert(_id, ["number", num.group(1)])
+                        self.structure.insert(_id, ["number", num.group("number")])
                 except Exception as e:
                     sys.stderr.write(
                         f"exception at line 470 of parser: {type(e)} {e}\n"
@@ -537,7 +572,6 @@ class ChgkParser:
                 element[1] = regexes["question"].sub("", element[1])
 
             # detect inner lists
-
             mo = {
                 m for m in re.finditer(r"(\s+|^)(\d+)[\.\)]\s*(?!\d)", element[1], re.U)
             }
@@ -608,7 +642,8 @@ class ChgkParser:
 
         for element in self.structure:
             if (
-                element[0] in set(["number", "tour", "tourrev", "question", "meta", "editor"])
+                element[0]
+                in set(["number", "tour", "tourrev", "question", "meta", "editor"])
                 and "question" in current_question
             ):
                 if self.defaultauthor and "author" not in current_question:
@@ -682,9 +717,13 @@ class ChgkParser:
         except ValueError:
             pass
 
+        tour_cnt = 0
         for i, element in enumerate(final_structure):
             if element[0] == "Question":
                 self.postprocess_question(element[1])
+            elif element[0] == "tour" and self.args.tour_numbers_as_words == "on":
+                element[1] = f"{self.TOUR_NUMBERS_AS_WORDS[tour_cnt]} тур"
+                tour_cnt += 1
 
         if debug:
             with codecs.open("debug_final.json", "w", "utf8") as f:

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/resources/regexes_by.json

@@ -1,7 +1,7 @@
 {
     "tour": "^(#\\s+)?Т[Уу][Рр]\\s?№?\\s?([0-9IVXLCDM]*)([\\.:])?$",
     "tourrev": "^([0-9IVXLCDM]+)\\s[Тт][Уу][Рр]([\\.:])?$",
-    "question": "П[Ыы][Тт][Аа][Нн][Ьь]?[Нн][Ее]\\s?[№N]?([0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
+    "question": "П[Ыы][Тт][Аа][Нн][Ьь]?[Нн][Ее]\\s?[№N]?(?P<number>[0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
     "handout": "Р[Аа][Зз][Дд][Аа][Тт]([Аа][Чч][Нн]|[Кк][Аа][Вв])[Ыы][\\s\\s][Мм][Аа][Тт][Ээ][Рр][Ыы][Яя][Лл][\\.:]",
     "answer": "А[Дд][Кк][Аа][Зз][Ыы]?\\s?[№N]?([0-9]+)?\\s?[\\.:]",
     "zachet": "З[Аа][Лл][Іі][Кк]\\s?[\\.:]",

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/resources/regexes_en.json

@@ -1,7 +1,7 @@
 {
     "tour": "^(#\\s+)?(B[Ll][Oo][Cc][Kk]|R[Oo][Uu][Nn][Dd])\\s?№?\\s?([0-9IVXLCDM]*)([\\.:])?$",
     "tourrev": "^([0-9IVXLCDM]+)\\s(B[Ll][Oo][Cc][Kk]|R[Oo][Uu][Nn][Dd])([\\.:])?$",
-    "question": "Q[Uu][Ee][Ss][Tt][Ii][Oo][Nn]\\s?[№N]?([0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
+    "question": "Q[Uu][Ee][Ss][Tt][Ii][Oo][Nn]\\s?[№N]?(?P<number>[0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
     "answer": "A[Nn][Ss][Ww][Ee][Rr]\\s?[№N]?([0-9]+)?\\s?[\\.:]",
     "handout": "^H[Aa][Nn][Dd][Oo][Uu][Tt][\\.:]",
     "zachet": "A[Cc][Ee][Pp][Tt]\\s?[\\.:]",

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/resources/regexes_kz_cyr.json

@@ -1,6 +1,6 @@
 {
     "tour": "^(#\\s+)?([0-9]+)\\s?[-–—]\\s?[Тт][Уу][Рр]\\s*$",
-    "question": "([0-9]+)\\s?[-–—]\\s?\\sС[Ұұ][Рр][Аа][Ққ]([\\.:]|\n|\r\n|$)",
+    "question": "(?P<number>[0-9]+)\\s?[-–—]\\s?\\sС[Ұұ][Рр][Аа][Ққ]([\\.:]|\n|\r\n|$)",
     "handout": "^Ү[Лл][Ее][Сс][Тт][Іі][Рр][Уу][\\s\\s][Мм][Аа][Тт][Ее][Рр][Ии][Аа][Лл][Ыы][\\.:]",
     "answer": "Ж[Аа][Уу][Аа][Пп]\\s?[№N]?([0-9]+)?\\s?[\\.:]",
     "zachet": "Қ[Аа][Бб][Ыы][Лл][Дд][Аа][Нн][Аа][Тт][Ыы][Нн]\\s[Жж][Аа][Уу][Аа][Пп](\\([Тт][Аа][Рр]\\))?\\s?[\\.:]",

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/resources/regexes_ru.json

@@ -1,7 +1,7 @@
 {
     "tour": "^(#\\s+)?Т[Уу][Рр]\\s?№?\\s?([0-9IVXLCDM]*)([\\.:])?$",
-    "tourrev": "^([0-9IVXLCDM]+)\\s[Тт][Уу][Рр]([\\.:])?$",
-    "question": "В[Оо][Пп][Рр][Оо][Сс]\\s?[№N]?([0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
+    "tourrev": "^([0-9IVXLCDM]+|[Пп][Ее][Рр][Вв][Ыы][Йй]|[Вв][Тт][Оо][Рр][Оо][Йй]|[Тт][Рр][Ее][Тт][Ии][Йй]|[Чч][Ее][Тт][Вв][Ее][Рр][Тт][Ыы][Йй]|[Пп][Яя][Тт][Ыы][Йй]|[Шш][Ее][Сс][Тт][Оо][Йй]|[Сс][Ее][Дд][Ьь][Мм][Оо][Йй]|[Вв][Оо][Сс][Ьь][Мм][Оо][Йй]|[Дд][Ее][Вв][Яя][Тт][Ыы][Йй]|[Дд][Ее][Сс][Яя][Тт][Ыы][Йй])\\s[Тт][Уу][Рр]([\\.:])?$",
+    "question": "^([Нн][Уу][Лл][Ее][Вв][Оо][Йй]|[Рр][Аа][Зз][Мм][Ии][Нн][Оо][Чч][Нн][Ыы][Йй])? ?[Вв][Оо][Пп][Рр][Оо][Сс]\\s?[№N]?(?P<number>[0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
     "handout": "^Р[Аа][Зз][Дд][Аа][Тт][Оо][Чч][Нн][Ыы][Йй]\\s+[Мм][Аа][Тт][Ее][Рр][Ии][Аа][Лл][\\.:]",
     "answer": "О[Тт][Вв][Ее][Тт][Ыы]?\\s?[№N]?([0-9]+)?\\s?[\\.:]",
     "zachet": "З[Аа][Чч][ЕеЁё][Тт]\\s?[\\.:]",

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/resources/regexes_sr.json

@@ -1,7 +1,7 @@
 {
     "tour": "^(#\\s+)?R[Uu][Nn][Dd][Aa]\\s?№?\\s?([0-9IVXLCDM]*)([\\.:])?$",
     "tourrev": "^([0-9IVXLCDM]+)\\sR[Uu][Nn][Dd][Aa]([\\.:])?$",
-    "question": "P[Ii][Tt][Aa][Nn][Jj][Ee]\\s?[№N]?([0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
+    "question": "P[Ii][Tt][Aa][Nn][Jj][Ee]\\s?[№N]?(?P<number>[0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
     "answer": "O[Dd][Gg][Oo][Vv][Oo][Rr]\\s?[№N]?([0-9]+)?\\s?[\\.:]",
     "handout": "^(M[Aa][Tt][Ee][Rr][Ii][Jj][Aa][Ll]|P[Oo][Dd][Ee][Ll][Jj][Ee][Nn][Oo])[\\.:]",
     "zachet": "P[Rr][Ii][Hh][Vv][Aa][Tt][Aa]\\s[Ss][Ee]\\s?[\\.:]",

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/resources/regexes_ua.json

@@ -1,7 +1,7 @@
 {
     "tour": "^(#\\s+)?Т[Уу][Рр]\\s?№?\\s?([0-9IVXLCDM]*)([\\.:])?$",
     "tourrev": "^([0-9IVXLCDM]+)\\s[Тт][Уу][Рр]([\\.:])?$",
-    "question": "З[Аа][Пп][Ии][Тт][Аа][Нн][Нн][Яя]\\s?[№N]?([0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
+    "question": "З[Аа][Пп][Ии][Тт][Аа][Нн][Нн][Яя]\\s?[№N]?(?P<number>[0-9\\s]*)\\s?([\\.:]|\n|\r\n|$)",
     "handout": "Р[Оо][Зз][Дд][Аа][Тт][Кк][Оо][Вв][Ии][Йй][\\s\\s][Мм][Аа][Тт][Ее][Рр][Іі][Аа][Лл][\\.:]",
     "answer": "В[Іі][Дд][Пп][Оо][Вв][Іі][Дд][Ьь]?\\s?[№N]?([0-9]+)?\\s?[\\.:]",
     "zachet": "З[Аа][Лл][Іі][Кк]\\s?[\\.:]",

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11}/chgksuite/resources/regexes_uz_cyr.json

@@ -1,6 +1,6 @@
 {
     "tour": "^(#\\s+)?([0-9]+)\\s?[-–—]\\s?[Тт][Уу][Рр]\\s*$",
-    "question": "([0-9]+)\\s?[-–—]\\s?\\sС[Аа][Вв][Оо][Лл]([\\.:]|\n|\r\n|$)",
+    "question": "(?P<number>[0-9]+)\\s?[-–—]\\s?\\sС[Аа][Вв][Оо][Лл]([\\.:]|\n|\r\n|$)",
     "answer": "Ж[Аа][Вв][Оо][Бб]\\s?[№N]?([0-9]+)?\\s?[\\.:]",
     "handout": "Т[Аа][Рр][Ққ][Аа][Тт][Мм][Аа][\\s\\s][Мм][Аа][Тт][Ее][Рр][Ии][Аа][Лл][\\.:]",
     "zachet": "Қ[Аа][Бб][Уу][Лл]\\s?[\\.:]",

chgksuite-0.26.0b11/chgksuite/version.py

@@ -0,0 +1 @@
+__version__ = "0.26.0b11"

{chgksuite-0.26.0b9 → chgksuite-0.26.0b11/chgksuite.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chgksuite
-Version: 0.26.0b9
+Version: 0.26.0b11
 Summary: A package for chgk automation
 Home-page: https://gitlab.com/peczony/chgksuite
 Author: Alexander Pecheny

chgksuite-0.26.0b9/chgksuite/version.py

@@ -1 +0,0 @@
-__version__ = "0.26.0b9"