infobox_football_biography task (bot)

tasks/infobox_football_biography/pseudocode_structure.md

@@ -0,0 +1,121 @@
+# Football Player Data Translation Bot - pseudocode structure
+
+## Observer Pattern: Monitoring and Error Handling
+
+```python
+class ErrorObserver:
+  def update(self, message):
+# Log error messages
+
+
+class ProgressObserver:
+  def update(self, message):
+# Log progress messages
+
+```
+
+## Pipeline Pattern: Structured Data Processing
+
+```python
+class DataExtractor:
+  def extract_data(self, article_url):
+    wikitext = self.fetch_wikitext(article_url)
+    parsed_data = self.parse_infobox_template(wikitext)
+    return parsed_data
+
+
+class DataTranslator:
+  def __init__(self, translation_array):
+    self.translation_array = translation_array
+
+  def translate(self, english_data):
+    # Translation logic using translation_array
+    pass
+
+
+class TemplateIntegrator:
+  def integrate(self, arabic_article_url, integrated_template):
+    arabic_wikitext = self.fetch_wikitext(arabic_article_url)
+    arabic_template = self.extract_arabic_template(arabic_wikitext)
+    # Integration logic using integrated_template
+    pass
+
+
+class QualityAssurer:
+  def validate_translation(self, translation):
+    # Validation logic
+    pass
+
+  def validate_integration(self, integrated_template):
+    # Validation logic
+    pass
+```
+
+## Decorator Pattern: Quality Assurance
+
+```python
+class TranslationQualityChecker:
+  def __init__(self, translator):
+    self.translator = translator
+
+  def translate(self, english_data):
+    translated_data = self.translator.translate(english_data)
+    # Validate translated_data
+    return translated_data
+
+
+class IntegrationQualityChecker:
+  def __init__(self, integrator):
+    self.integrator = integrator
+
+  def integrate(self, arabic_article_url, integrated_template):
+    self.integrator.integrate(arabic_article_url, integrated_template)
+    # Validate integrated_template
+```
+
+## Template Method Pattern: Bot Operation Structure
+
+```python
+
+class FootballPlayerBot:
+  def __init__(self):
+    self.error_observer = ErrorObserver()
+    self.progress_observer = ProgressObserver()
+    self.translation_array = load_custom_translation_array()
+
+  def notify_error(self, message):
+    self.error_observer.update(message)
+
+  def notify_progress(self, message):
+    self.progress_observer.update(message)
+
+  # ... (Other methods)
+
+  def bot_operation(self):
+    self.notify_progress("Starting bot operation...")
+
+    data_extractor = DataExtractor()
+    data_translator = DataTranslator(self.translation_array)
+    template_integrator = TemplateIntegrator()
+
+    quality_translator = TranslationQualityChecker(data_translator)
+    quality_integrator = IntegrationQualityChecker(template_integrator)
+
+    for each article in English Wikipedia:
+      english_data = data_extractor.extract_data(article.url)
+      translated_data = quality_translator.translate(english_data)
+
+      arabic_wikitext = self.fetch_wikitext(article.arabic_url)
+      integrated_template = quality_integrator.integrate(article.arabic_url, translated_data)
+
+      # ... (Other steps)
+
+    self.notify_progress("Bot operation completed.")
+```
+
+# Instantiate and run the bot
+
+```python
+bot = FootballPlayerBot()
+bot.bot_operation()
+```

tasks/infobox_football_biography/run.py

@@ -0,0 +1,22 @@
+import pywikibot
+
+from tasks.infobox_football_biography.src.data_extraction.templates.infobox_football_biography import \
+    InfoboxFootballBiography
+from tasks.infobox_football_biography.src.football_player_bot import FootballPlayerBot
+
+bot = FootballPlayerBot()
+
+site = pywikibot.Site("en", "wikipedia")
+page_title = "Paul_Abasolo"
+page = pywikibot.Page(site, page_title)
+
+template = InfoboxFootballBiography(
+    logger=bot.getChainOfLoggers(),
+    text_page=page.text
+)
+
+template.parse()
+template.template_name()
+template.parameters_list()
+if template.check():
+    template.list.sort(key=lambda x: x["name"])

tasks/infobox_football_biography/src/data_extraction/data_extractor.py

@@ -0,0 +1,52 @@
+from abc import abstractmethod, ABC
+
+import wikitextparser as wtp
+
+from core.utils.helpers import prepare_str
+from tasks.infobox_football_biography.src.logger.abstract_logger import AbstractLogger
+
+
+class DataExtractor(ABC):
+    def __init__(self, text_page: str, logger: AbstractLogger):
+        self.text_page = text_page
+        self.logger = logger
+        self.list = []
+
+    @abstractmethod
+    def template_name(self) -> str:
+        pass
+
+    @abstractmethod
+    def parameters_list(self) -> list:
+        pass
+
+    def check(self) -> bool:
+        return len(self.list) > 0
+
+    def parse(self):
+        self.logger.logMessage(AbstractLogger.INFO, "start extract data")
+        parsed = wtp.parse(self.text_page)
+        self.logger.logMessage(AbstractLogger.INFO, "end extract data")
+        self.logger.logMessage(AbstractLogger.INFO, "start extract template")
+        templates = parsed.templates
+        if not len(templates):
+            self.logger.logMessage(AbstractLogger.WARNING, "no template found in page")
+            return
+        if self.template_name() is None:
+            self.logger.logMessage(AbstractLogger.ERROR, "no template name set in class you are using")
+            return
+        if self.parameters_list() is None or len(self.parameters_list()) == 0:
+            self.logger.logMessage(AbstractLogger.ERROR, "no parameters set in class you are using")
+            return
+        for template in templates:
+            if prepare_str(template.name) == prepare_str(self.template_name()):
+                self.logger.logMessage(AbstractLogger.INFO, "start extract parameters")
+                for parameter in self.parameters_list():
+                    for param in template.arguments:
+                        if prepare_str(param.name) == prepare_str(parameter):
+                            self.logger.logMessage(AbstractLogger.INFO, f"{param.name}: {param.value}")
+                            self.list.append({
+                                "name": param.name,
+                                "value": param.value
+                            })
+                break

tasks/infobox_football_biography/src/data_extraction/templates/infobox_football_biography.py

@@ -0,0 +1,36 @@
+from abc import ABC
+
+from tasks.infobox_football_biography.src.data_extraction.data_extractor import DataExtractor
+from tasks.infobox_football_biography.src.logger.abstract_logger import AbstractLogger
+
+
+class InfoboxFootballBiography(DataExtractor, ABC):
+    def __init__(self, text_page: str, logger: AbstractLogger):
+        super().__init__(text_page=text_page, logger=logger)
+
+    def template_name(self) -> str:
+        return "Infobox football biography"
+
+    def parameters_list(self) -> list:
+        return [
+            "position",
+            "years1", "clubs1", "caps1", "goals1",
+            "years2", "clubs2", "caps2", "goals2",
+            "years3", "clubs3", "caps3", "goals3",
+            "years4", "clubs4", "caps4", "goals4",
+            "years5", "clubs5", "caps5", "goals5",
+            "years6", "clubs6", "caps6", "goals6",
+            "years7", "clubs7", "caps7", "goals7",
+            "years8", "clubs8", "caps8", "goals8",
+            "years9", "clubs9", "caps9", "goals9",
+            "years10", "clubs10", "caps10", "goals10",
+            "years11", "clubs11", "caps11", "goals11",
+            "years12", "clubs12", "caps12", "goals12",
+            "years13", "clubs13", "caps13", "goals13",
+            "years14", "clubs14", "caps14", "goals14",
+            "years15", "clubs15", "caps15", "goals15",
+            "years16", "clubs16", "caps16", "goals16",
+            "years17", "clubs17", "caps17", "goals17",
+            "years18", "clubs18", "caps18", "goals18",
+            "years19", "clubs19", "caps19", "goals19",
+        ]

tasks/infobox_football_biography/src/data_translator/classification_context.py

@@ -0,0 +1,13 @@
+class ClassificationContext:
+    def __init__(self):
+        self.strategies = []
+
+    def add_strategy(self, strategy):
+        self.strategies.append(strategy)
+
+    def classify(self, value):
+        for strategy in self.strategies:
+            result = strategy.classify(value)
+            if result:
+                return result
+        return "unknown"

tasks/infobox_football_biography/src/data_translator/data_classification/normal_text_classification_strategy.py

@@ -0,0 +1,7 @@
+from tasks.infobox_football_biography.src.data_translator.value_classification_strategy import \
+    ValueClassificationStrategy
+
+
+class NormalTextClassificationStrategy(ValueClassificationStrategy):
+    def classify(self, value):
+        return "normal_text"

tasks/infobox_football_biography/src/data_translator/data_classification/number_classification_strategy.py

@@ -0,0 +1,11 @@
+from tasks.infobox_football_biography.src.data_translator.value_classification_strategy import \
+    ValueClassificationStrategy
+
+
+class NumberClassificationStrategy(ValueClassificationStrategy):
+    def classify(self, value):
+        try:
+            float(value)
+            return "number"
+        except ValueError:
+            return None

tasks/infobox_football_biography/src/data_translator/data_classification/wikilink_classification_strategy.py

@@ -0,0 +1,10 @@
+from tasks.infobox_football_biography.src.data_translator.value_classification_strategy import \
+    ValueClassificationStrategy
+
+
+class WikiLinkClassificationStrategy(ValueClassificationStrategy):
+    def classify(self, value):
+        # todo: use wpikitextparser
+        if value.startswith("[[") and value.endswith("]]"):
+            return "wiki_link"
+        return None

tasks/infobox_football_biography/src/data_translator/data_translation/normal_text_translation_handler.py

@@ -0,0 +1,7 @@
+from tasks.infobox_football_biography.src.data_translator.data_translation_handler import DataTranslationHandler
+
+
+class NormalTextTranslationHandler(DataTranslationHandler):
+    def translate(self, value):
+        # Translate the normal text to Arabic (implement this logic)
+        return value

tasks/infobox_football_biography/src/data_translator/data_translation/number_translation_handler.py

@@ -0,0 +1,7 @@
+from tasks.infobox_football_biography.src.data_translator.data_translation_handler import DataTranslationHandler
+
+
+class NumberTranslationHandler(DataTranslationHandler):
+    def translate(self, value):
+        # Translate the number to Arabic
+        return str(value)

tasks/infobox_football_biography/src/data_translator/data_translation/wikilink_translation_handler.py

@@ -0,0 +1,7 @@
+from tasks.infobox_football_biography.src.data_translator.data_translation_handler import DataTranslationHandler
+
+
+class WikiLinkTranslationHandler(DataTranslationHandler):
+    def translate(self, value):
+        # Translate the wiki link to Arabic (implement this logic)
+        return value

tasks/infobox_football_biography/src/data_translator/data_translation_handler.py

@@ -0,0 +1,7 @@
+from abc import abstractmethod, ABC
+
+
+class DataTranslationHandler(ABC):
+    @abstractmethod
+    def translate(self, value):
+        pass

tasks/infobox_football_biography/src/data_translator/translation_chain.py

@@ -0,0 +1,13 @@
+class TranslationChain:
+    def __init__(self):
+        self.handlers = []
+
+    def add_handler(self, handler):
+        self.handlers.append(handler)
+
+    def translate(self, value):
+        for handler in self.handlers:
+            translated_value = handler.translate(value)
+            if translated_value:
+                return translated_value
+        return value

tasks/infobox_football_biography/src/data_translator/value_classification_strategy.py

@@ -0,0 +1,7 @@
+from abc import abstractmethod, ABC
+
+
+class ValueClassificationStrategy(ABC):
+    @abstractmethod
+    def classify(self, value):
+        pass

tasks/infobox_football_biography/src/football_player_bot.py

@@ -0,0 +1,24 @@
+from tasks.infobox_football_biography.src.logger.abstract_logger import AbstractLogger
+from tasks.infobox_football_biography.src.logger.console_logger import ConsoleLogger
+from tasks.infobox_football_biography.src.logger.error_logger import ErrorLogger
+from tasks.infobox_football_biography.src.logger.file_logger import FileLogger
+
+
+class FootballPlayerBot:
+
+    def getChainOfLoggers(self) -> AbstractLogger:
+        errorLogger = ErrorLogger(AbstractLogger.ERROR)
+        fileLogger = FileLogger(AbstractLogger.DEBUG)
+        consoleLogger = ConsoleLogger(AbstractLogger.INFO)
+
+        errorLogger.nextLogger = fileLogger
+        fileLogger.nextLogger = consoleLogger
+
+        return errorLogger
+
+    def __init__(self):
+        self.logger = self.getChainOfLoggers()
+
+        self.logger.logMessage(AbstractLogger.INFO, "Start")
+        self.logger.logMessage(AbstractLogger.DEBUG, "debug message")
+        self.logger.logMessage(AbstractLogger.ERROR, "error message")

tasks/infobox_football_biography/src/logger/abstract_logger.py

@@ -0,0 +1,31 @@
+from abc import ABC, abstractmethod
+
+
+class AbstractLogger(ABC):
+    INFO: int = 1
+    DEBUG: int = 2
+    WARNING: int = 3
+    ERROR: int = 4
+    FATAL: int = 5
+
+    _level: int = None
+    # next element in chain or responsibility
+    _nextLogger = None
+
+    @property
+    def nextLogger(self):
+        return self._nextLogger
+
+    @nextLogger.setter
+    def nextLogger(self, value):
+        self._nextLogger = value
+
+    def logMessage(self, level, message):
+        if self._level <= level:
+            self.write(message)
+        if self._nextLogger is not None:
+            self._nextLogger.logMessage(level, message)
+
+    @abstractmethod
+    def write(self, message):
+        pass