chore: typo fix (#1465)

* typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

---------

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

docling/backend/md_backend.py

@@ -409,7 +409,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                         )
                     return _txt
 
-                # restore original HTML by removing previouly added markers
+                # restore original HTML by removing previously added markers
                 for regex in [
                     rf"<pre>\s*<code>\s*{_START_MARKER}",
                     rf"{_STOP_MARKER}\s*</code>\s*</pre>",

docling/backend/msword_backend.py

@@ -436,7 +436,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
 
         # Common styles for bullet and numbered lists.
         # "List Bullet", "List Number", "List Paragraph"
-        # Identify wether list is a numbered list or not
+        # Identify whether list is a numbered list or not
         # is_numbered = "List Bullet" not in paragraph.style.name
         is_numbered = False
         p_style_id, p_level = self._get_label_and_level(paragraph)

docling/backend/xml/jats_backend.py

@@ -91,7 +91,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
         super().__init__(in_doc, path_or_stream)
         self.path_or_stream = path_or_stream
 
-        # Initialize the root of the document hiearchy
+        # Initialize the root of the document hierarchy
         self.root: Optional[NodeItem] = None
 
         self.valid = False

docling/backend/xml/uspto_backend.py

@@ -1,6 +1,6 @@
 """Backend to parse patents from the United States Patent Office (USPTO).
 
-The parsers included in this module can handle patent grants pubished since 1976 and
+The parsers included in this module can handle patent grants published since 1976 and
 patent applications since 2001.
 The original files can be found in https://bulkdata.uspto.gov.
 """
@@ -440,7 +440,7 @@ class PatentUsptoIce(PatentUspto):
                     )
 
             elif name == self.Element.PARAGRAPH.value and text:
-                # remmove blank spaces added in paragraphs
+                # remove blank spaces added in paragraphs
                 text = re.sub("\\s+", " ", text)
                 if self.Element.ABSTRACT.value in self.property:
                     self.abstract = (
@@ -1697,7 +1697,7 @@ class XmlTable:
 class HtmlEntity:
     """Provide utility functions to get the HTML entities of styled characters.
 
-    This class has been developped from:
+    This class has been developed from:
     https://unicode-table.com/en/html-entities/
     https://www.w3.org/TR/WD-math-970515/table03.html
     """
@@ -1896,7 +1896,7 @@ class HtmlEntity:
         """Get an HTML entity of a greek letter in ISO 8879.
 
         Args:
-            The text to transform, as an ISO 8879 entitiy.
+            The text to transform, as an ISO 8879 entity.
 
         Returns:
             The HTML entity representing a greek letter. If the input text is not

docling/cli/main.py

@@ -521,7 +521,7 @@ def convert(  # noqa: C901
             if image_export_mode != ImageRefMode.PLACEHOLDER:
                 pipeline_options.generate_page_images = True
                 pipeline_options.generate_picture_images = (
-                    True  # FIXME: to be deprecated in verson 3
+                    True  # FIXME: to be deprecated in version 3
                 )
                 pipeline_options.images_scale = 2
 

docling/models/table_structure_model.py

@@ -234,7 +234,7 @@ class TableStructureModel(BasePageModel):
                                 tcells = table_cluster.cells
                             tokens = []
                             for c in tcells:
-                                # Only allow non empty stings (spaces) into the cells of a table
+                                # Only allow non empty strings (spaces) into the cells of a table
                                 if len(c.text.strip()) > 0:
                                     new_cell = copy.deepcopy(c)
                                     new_cell.rect = BoundingRectangle.from_bounding_box(

docling/models/tesseract_ocr_model.py

@@ -151,7 +151,7 @@ class TesseractOcrModel(BaseOcrModel):
                             script = map_tesseract_script(script)
                             lang = f"{self.script_prefix}{script}"
 
-                            # Check if the detected languge is present in the system
+                            # Check if the detected language is present in the system
                             if lang not in self._tesserocr_languages:
                                 msg = f"Tesseract detected the script '{script}' and language '{lang}'."
                                 msg += " However this language is not installed in your system and will be ignored."