Feature: fix datetime Spanish

kindle2notion/exporting.py

@@ -16,11 +16,11 @@
 
 
 def export_to_notion(
-    all_books: Dict,
-    enable_highlight_date: bool,
-    enable_book_cover: bool,
-    notion_api_auth_token: str,
-    notion_database_id: str,
+        all_books: Dict,
+        enable_highlight_date: bool,
+        enable_book_cover: bool,
+        notion_api_auth_token: str,
+        notion_database_id: str,
 ) -> None:
     print("Initiating transfer...\n")
 
@@ -48,7 +48,7 @@ def export_to_notion(
 
 
 def _prepare_aggregated_text_for_one_book(
-    clippings: List, enable_highlight_date: bool
+        clippings: List, enable_highlight_date: bool
 ) -> Tuple[str, str]:
     # TODO: Special case for books with len(clippings) >= 100 characters. Character limit in a Paragraph block in Notion is 100
     formatted_clippings = []
@@ -77,17 +77,17 @@ def _prepare_aggregated_text_for_one_book(
 
 
 def _add_book_to_notion(
-    title: str,
-    author: str,
-    clippings_count: int,
-    formatted_clippings: list,
-    last_date: str,
-    notion_api_auth_token: str,
-    notion_database_id: str,
-    enable_book_cover: bool,
+        title: str,
+        author: str,
+        clippings_count: int,
+        formatted_clippings: list,
+        last_date_string: str,
+        notion_api_auth_token: str,
+        notion_database_id: str,
+        enable_book_cover: bool,
 ):
     notion = notional.connect(auth=notion_api_auth_token)
-    last_date = datetime.strptime(last_date, "%A, %d %B %Y %I:%M:%S %p")
+    last_date = __get_last_date_from_string(last_date_string)
 
     # Condition variables
     title_exists = False
@@ -174,6 +174,15 @@ def _add_book_to_notion(
     return message
 
 
+def __get_last_date_from_string(last_date_string: str) -> datetime:
+    if not last_date_string:
+        return datetime.now()
+    try:
+        return datetime.strptime(last_date_string, "%A, %d %B %Y %I:%M:%S %p")
+    except ValueError:
+        # Datetime format is not English, retrying with non AM-PM format
+        return datetime.strptime(last_date_string, "%A, %d %B %Y %H:%M:%S")
+
 # def _create_rich_text_object(text):
 #     if "Note: " in text:
 #         # Bold text

kindle2notion/languages/enums.py

@@ -0,0 +1,38 @@
+from enum import Enum
+
+
+class Locale(Enum):
+    # Enum containing languages
+    ENGLISH = "en"
+    SPANISH = "es"
+
+    def __str__(self):
+        return self.value
+
+
+class Word(Enum):
+    # For each word, we have to handle different languages
+    NOTE = {
+        Locale.ENGLISH: "note",
+        Locale.SPANISH: "nota"
+    }
+    LOCATION = {
+        Locale.ENGLISH: "location",
+        Locale.SPANISH: "posición",
+    }
+    PAGE = {
+        Locale.ENGLISH: "page",
+        Locale.SPANISH: "página",
+    }
+    DATE_ADDED = {
+        Locale.ENGLISH: "added on",
+        Locale.SPANISH: "añadido el",
+    }
+    # Date formats also depend on language
+    DATE_FORMAT = {
+        Locale.ENGLISH: "%A, %d %B %Y %I:%M:%S %p",
+        Locale.SPANISH: "%A, %d %B %Y %H:%M:%S",
+    }
+
+    def __str__(self, language=Locale.ENGLISH):
+        return self.value[language]

kindle2notion/languages/word_detector.py

@@ -0,0 +1,24 @@
+from typing import List
+
+from kindle2notion.languages.enums import Word, Locale
+
+
+class WordDetector:
+
+    def __init__(self, languages: List[Locale]):
+        self.languages = languages
+        self.language_words = {lang: set() for lang in languages}
+
+        for word in Word:
+            for lang in word.value:
+                self.language_words[lang].add(word.value[lang])
+
+    def detect(self, text):
+        scores = {lang: 0 for lang in self.languages}
+        for lang, words in self.language_words.items():
+            scores[lang] = sum([len(word) for word in words if self.has_word(text, word)])
+        return max(scores, key=scores.get)
+
+    def has_word(self, text, word):
+        return word.lower() in text.lower()
+

kindle2notion/parsing.py

@@ -1,8 +1,12 @@
+from datetime import datetime
 from re import findall
 from typing import Dict, List, Tuple
 
 from dateparser import parse
 
+from kindle2notion.languages.word_detector import WordDetector
+from kindle2notion.languages.enums import Locale, Word
+
 BOOKS_WO_AUTHORS = []
 
 ACADEMIC_TITLES = [
@@ -80,6 +84,8 @@
 
 DELIMITERS = ["; ", " & ", " and "]
 
+WORD_DETECTOR = WordDetector([language for language in Locale])
+
 
 def parse_raw_clippings_text(raw_clippings_text: str) -> Dict:
     raw_clippings_list = raw_clippings_text.split("==========")
@@ -126,26 +132,34 @@ def _parse_page_location_date_and_note(
     second_line_as_list = second_line.strip().split(" | ")
     page = location = date = ""
     is_note = False
-
     for element in second_line_as_list:
         element = element.lower()
-        if "note" in element:
+        language: Locale = WORD_DETECTOR.detect(element)
+        if Word.NOTE.value[language] in element:
             is_note = True
-        if "page" in element:
-            page = element[element.find("page") :].replace("page", "").strip()
-        if "location" in element:
-            location = (
-                element[element.find("location") :].replace("location", "").strip()
-            )
-        if "added on" in element:
-            date = parse(
-                element[element.find("added on") :].replace("added on", "").strip()
+        if is_word_in_element(element, language, Word.PAGE):
+            page = _parse_word_from_element(element, language, Word.PAGE)
+        if is_word_in_element(element, language, Word.LOCATION):
+            location = _parse_word_from_element(element, language, Word.LOCATION)
+        if is_word_in_element(element, language, Word.DATE_ADDED):
+            date_string = _parse_word_from_element(element, language, Word.DATE_ADDED)
+            date_parsed: datetime = parse(
+                date_string, languages=[language.value for language in Locale]
             )
-            date = date.strftime("%A, %d %B %Y %I:%M:%S %p")
+            date = date_parsed.strftime(Word.DATE_FORMAT.value[language])
 
     return page, location, date, is_note
 
 
+def is_word_in_element(element: str, language: Locale, word: Word):
+    return word.value[language] in element
+
+
+def _parse_word_from_element(element: str, language: Locale, word: Word):
+    word_value_in_language = word.value[language]
+    return element[element.find(word_value_in_language):].replace(word_value_in_language, "").strip()
+
+
 def _add_parsed_items_to_all_books_dict(
     all_books: Dict,
     title: str,

setup.py

@@ -11,7 +11,7 @@
 
 setup(
     name="kindle2notion",
-    version="1.0.1",
+    version="1.0.2",
     author="Jeffrey Jacob",
     author_email="[email protected]",
     description="Export all the clippings from your Kindle device to a database in Notion.",

tests/test_exporting.py

@@ -71,3 +71,43 @@ def test_prepare_aggregated_text_for_one_book_should_return_the_aggregated_text_
     print(actual)
     # Then
     assert expected == actual
+
+
+def test_when_date_is_not_ampm_format_then_aggregated_text_should_return_appropiate_date():
+    # Given
+    highlights = [
+        (
+            "This is an example highlight.",
+            "1",
+            "100",
+            "jueves, 24 de agosto de 2023 7:28:38",
+            False,
+        ),
+        (
+            "This is a second example highlight.",
+            "2",
+            "200",
+            "viernes, 25 de agosto de 2023 7:28:38",
+            True,
+        ),
+    ]
+
+    expected = (
+        [
+            "This is an example highlight.\n* Page: 1, Location: 100, Date Added: jueves, 24 de agosto de 2023 7:28:38\n\n",
+            "> NOTE: \nThis is a second example highlight.\n* Page: 2, Location: 200, Date Added: viernes, 25 de agosto de 2023 7:28:38\n\n",
+        ],
+        "viernes, 25 de agosto de 2023 7:28:38",
+    )
+
+    # When
+    actual = _prepare_aggregated_text_for_one_book(
+        highlights, enable_highlight_date=True
+    )
+    print(actual)
+    # Then
+    assert expected == actual
+
+
+def test_when_date_is_not_ampm_format_then_aggregated_text_should_not_give_valueerror():
+    pass

tests/test_parsing.py

@@ -333,3 +333,20 @@ def test_add_parsed_items_to_books_dict_should_add_the_parsed_items_when_the_boo
 
     # Then
     assert expected == actual
+
+def test_parse_date_when_format_does_not_include_am_pm():
+    # Given
+    raw_clipping_list = [
+        "Relativity (Einstein, Albert)",
+        "- La subrayado en la posición 558-560 | Añadido el viernes, 25 de agosto de 2023 7:28:38",
+        "",
+        "This is a test highlight.",
+        False,
+    ]
+    expected = ("3", "", "Friday, 30 April 2021 12:31:29 AM", False)
+
+    # When
+    actual = _parse_page_location_date_and_note(raw_clipping_list)
+
+    # Then
+    assert expected == actual