Fixed pylint warnings

libpdf/core.py

@@ -208,13 +208,13 @@ def main_api(  # pylint: disable=too-many-arguments
             for visual_incl_element in visual_debug_include_elements:
                 if visual_incl_element not in RENDER_ELEMENTS:
                     raise ValueError(
-                        'Given visual included elements {} not in {}'.format(visual_incl_element, RENDER_ELEMENTS),
+                        f'Given visual included elements {visual_incl_element} not in {RENDER_ELEMENTS}',
                     )
         if visual_debug_exclude_elements:
             for visual_excl_element in visual_debug_exclude_elements:
                 if visual_excl_element not in RENDER_ELEMENTS:
                     raise ValueError(
-                        'Given visual excluded elements {} not in {}'.format(visual_excl_element, RENDER_ELEMENTS),
+                        f'Given visual excluded elements {visual_excl_element} not in {RENDER_ELEMENTS}',
                     )
         if visual_debug_include_elements and visual_debug_exclude_elements:
             raise ValueError('Can not visual include and exclude at the same time.')
@@ -330,15 +330,12 @@ def handle_parse_result(self, ctx, opts, args):
         """Handle parse result."""
         if (not self.depends_on.intersection(opts)) and self.name in opts:
             raise click.UsageError(
-                "Illegal usage: '{}' depends on "
-                "'{}' which is not given.".format(self.name, ', '.join(self.depends_on)),
+                f"Illegal usage: '{self.name}' depends on '{', '.join(self.depends_on)}' which is not given.",
             )
         if self.mutually_exclusive.intersection(opts) and self.name in opts:
             raise click.UsageError(
-                "Illegal usage: '{}' is mutually exclusive with '{}' which is also given.".format(
-                    self.name,
-                    ', '.join(self.mutually_exclusive),
-                ),
+                f"Illegal usage: '{self.name}' is mutually exclusive with '{', '.join(self.mutually_exclusive)}' "
+                "which is also given."
             )
 
         return super().handle_parse_result(ctx, opts, args)

libpdf/extract.py

@@ -45,7 +45,7 @@ class FoldedStr(str):
 
 def folded_str_representer(dumper, text):
     """Warp function of the representer."""
-    return dumper.represent_scalar(u'tag', text, style='>')
+    return dumper.represent_scalar('tag', text, style='>')
 
 
 yaml.add_representer(FoldedStr, folded_str_representer)
@@ -257,8 +257,7 @@ def smart_page_crop_header_footer(  # pylint: disable=too-many-branches, too-man
                         ):
                             element_cnt += 1
                     # on one page several header elements may have same y coordination but count only once
-                    if element_cnt > 1:
-                        element_cnt = 1
+                    element_cnt = min(element_cnt, 1)
                     page_cnt = page_cnt + element_cnt
             # occur on more than HEADER_FOOTER_OCCURRENCE_PERCENTAGE pages, considered as header element
             # and remove from list
@@ -291,8 +290,7 @@ def smart_page_crop_header_footer(  # pylint: disable=too-many-branches, too-man
                         ):
                             element_cnt += 1
                     # on one page several footer elements may have same y coordination but count only once
-                    if element_cnt > 1:
-                        element_cnt = 1
+                    element_cnt = min(element_cnt, 1)
                     page_cnt = page_cnt + element_cnt
             # occur on more than HEADER_FOOTER_OCCURRENCE_PERCENTAGE pages, considered as footer element
             # and remove from list
@@ -343,9 +341,9 @@ def check_false_positive_header_footer(pdf, elements_list):  # pylint: disable=t
     # search the lowest element height on each page
     element_low_pos_dict = {}
     for page_num, elements in elements_page_dict.items():
-        lowest_element_pos = float('{:.4f}'.format(elements[0].position.y0))  # restrict to 4 digits precision
+        lowest_element_pos = float(f'{elements[0].position.y0:.4f}')  # restrict to 4 digits precision
         for element in elements:
-            lowest_element_pos = min(lowest_element_pos, float('{:.4f}'.format(element.position.y0)))
+            lowest_element_pos = min(lowest_element_pos, float(f'{element.position.y0:.4f}'))
         element_low_pos_dict[page_num] = lowest_element_pos
 
     start_page_low_pos = list(element_low_pos_dict)[0]
@@ -376,7 +374,7 @@ def check_false_positive_header_footer(pdf, elements_list):  # pylint: disable=t
                 UNIQUE_HEADER_OR_FOOTER_ELEMENTS_PERCENTAGE * len(pdf.pages),
             ):
                 for idx, element in enumerate(elements_list):
-                    if float('{:.4f}'.format(element.position.y0)) == header_low_pos:
+                    if float(f'{element.position.y0:.4f}') == header_low_pos:
                         del elements_list[idx]
                 # recursively check again, to find the next min_low_pos, which will determine the header/footer boundary
                 if elements_list:
@@ -386,7 +384,7 @@ def check_false_positive_header_footer(pdf, elements_list):  # pylint: disable=t
                 elements_list.pop()
     else:
         for idx, element in enumerate(elements_list):
-            if float('{:.4f}'.format(element.position.y0)) == header_low_pos:
+            if float(f'{element.position.y0:.4f}') == header_low_pos:
                 del elements_list[idx]
         # recursively check again, to find the next min_low_pos, which will determine the header/footer boundary
         if elements_list:

libpdf/log.py

@@ -13,8 +13,7 @@
 
 def get_level_name(verbose):
     """Return the log levels for the CLI verbosity flag in words."""
-    if verbose > 3:
-        verbose = 3
+    verbose = min(verbose, 3)
     level_dict = {
         0: 'ERROR/FATAL/CRITICAL',
         1: 'WARNING',

libpdf/models/model_base.py

@@ -36,5 +36,5 @@ def check(self):
     def __repr__(self):
         """Overwrite the object representation for better debugging."""
         if hasattr(self, 'id_'):
-            return '{0}({1!r})'.format(self.__class__.__name__, self.id_)  # pylint: disable=no-member
-        return '{0}()'.format(self.__class__.__name__)
+            return f'{self.__class__.__name__}({self.id_!r})'  # pylint: disable=no-member
+        return f'{self.__class__.__name__}()'

libpdf/process.py

@@ -54,7 +54,7 @@ class MyRepresenter(RoundTripRepresenter):  # pylint: disable=too-few-public-met
 
     def represent_mapping(self, tag, mapping, flow_style=None):
         """Override represent_mapping."""
-        tag = u'tag:yaml.org,2002:map'
+        tag = 'tag:yaml.org,2002:map'
 
         return RoundTripRepresenter.represent_mapping(self, tag, mapping, flow_style=flow_style)
 
@@ -161,7 +161,7 @@ def output_dump(output_format: str, output_path: str, objects: ApiObjects):
         if output_dir:
             if not os.path.isdir(output_dir):
                 os.makedirs(output_dir)
-        with open(output_path, 'w') as file:
+        with open(output_path, 'w', encoding='utf-8') as file:
             if output_format == 'json':
                 json_string = json.dumps(output_dict, default=json_datetime_converter, indent=2, sort_keys=False)
                 file.write(json_string)

libpdf/tables.py

@@ -42,7 +42,7 @@ class FoldedStr(str):
 
 def folded_str_representer(dumper, text):
     """Warp function of the representer."""
-    return dumper.represent_scalar(u'tag', text, style='>')
+    return dumper.represent_scalar('tag', text, style='>')
 
 
 def extract_pdf_table(pdf, pages_list: List[Page], figure_list: List[Figure]):

libpdf/textbox.py

@@ -299,8 +299,7 @@ def chapter_examiner(chapter: Dict, lt_textboxes: List[LTTextBox], page: Page) -
     # This assumption may not work in PDFs with multiple columns.
     y0 = chapter['position']['y1'] - (page.height / 4)
     y1 = chapter['position']['y1'] + (page.height / 4)
-    if y0 < 0:
-        y0 = 0
+    y0 = max(y0, 0)
     if y1 > page.height:
         y1 = page.height
 

libpdf/utils.py

@@ -811,10 +811,10 @@ def visual_debug_pdfminer(pdf_path, vd_pdfminer_output):
 def extract_layout(path_pdf, idx_single_page=None):
     """Use pdfminer.six to extract LTContainer layout boxes."""
     LOG.info('Extracting layout ...')
-    file_pointer = open(path_pdf, 'rb')
-
-    # init pdfminer elements
-    parser = PDFParser(file_pointer)
+    parser = None
+    with open(path_pdf, 'rb') as file_pointer:
+        # init pdfminer elements
+        parser = PDFParser(file_pointer)
     doc = PDFDocument(parser)
     rsrcmgr = PDFResourceManager()
     laparams = LAParams(char_margin=6, line_margin=0.4)