tidied code to be flake8 compliant

Author: petermr

.github/workflows/ci.yml

@@ -48,7 +48,7 @@ jobs:
         # stop the build if there are Python syntax errors or undefined names
         flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
         # exit-zero treats all errors as warnings
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=88 --statistics
         
     - name: Check code formatting with black
       run: |

corpus_module/corpus.py

@@ -52,9 +52,7 @@ def __init__(
         """
         self.topdir = Path(topdir) if topdir else None
         if self.topdir and not self.topdir.is_dir():
-            raise ValueError(
-                f"AmiCorpus() requires valid directory {self.topdir}"
-            )
+            raise ValueError(f"AmiCorpus() requires valid directory {self.topdir}")
 
         self.container_by_file = dict()
         # rootnode
@@ -154,9 +152,7 @@ def make_descendants(self, file: Optional[Union[str, Path]] = None):
         if file is None:
             file = self.root_dir
         if file is None or not Path(file).is_dir():
-            logger.error(
-                f"Cannot make file children for {file}"
-            )
+            logger.error(f"Cannot make file children for {file}")
             return
         files = self._get_children(file)
         for f in files:
@@ -269,9 +265,7 @@ def read_json_create_write_html_table(
 
             # Write to file
             with open(outfile_h, "w", encoding="utf-8") as f:
-                f.write(
-                    ET.tostring(htmlx, encoding="unicode", pretty_print=True)
-                )
+                f.write(ET.tostring(htmlx, encoding="unicode", pretty_print=True))
 
     def list_files(self, globstr: str) -> List[Path]:
         """
@@ -284,9 +278,7 @@ def list_files(self, globstr: str) -> List[Path]:
             List of matching file paths
         """
         if globstr and self.root_dir:
-            return self._posix_glob(
-                str(self.root_dir / globstr), recursive=True
-            )
+            return self._posix_glob(str(self.root_dir / globstr), recursive=True)
         return []
 
     def create_datatables_html_with_filenames(
@@ -358,9 +350,7 @@ def make_infiles(self, maxfiles: int = 999999999) -> List[Path]:
             List of file paths
         """
         if self.globstr:
-            self.infiles = self._posix_glob(
-                self.globstr, recursive=True
-            )[:maxfiles]
+            self.infiles = self._posix_glob(self.globstr, recursive=True)[:maxfiles]
         return self.infiles
 
     def _make_outfile(self):
@@ -424,23 +414,15 @@ def search_files_with_queries(
         for query_id in query_ids:
             query = self.corpus_queries.get(query_id)
             if query is None:
-                err_msg = (
-                    "cannot find query: "
-                    + str(query_id)
-                )
+                err_msg = "cannot find query: " + str(query_id)
                 logger.error(err_msg)
                 continue
-            dbg_msg = (
-                "outfile==> "
-                + str(query.outfile)
-            )
+            dbg_msg = "outfile==> " + str(query.outfile)
             logger.debug(dbg_msg)
 
             # This would need to be implemented based on the search functionality
             # For now, we'll create a placeholder
-            logger.info(
-                f"Running query: {query_id}"
-            )
+            logger.info(f"Running query: {query_id}")
 
         return html_by_query_id
 
@@ -487,9 +469,7 @@ def __init__(
             exist_ok: Whether to allow existing directory
         """
         if not isinstance(ami_corpus, AmiCorpus):
-            raise ValueError(
-                f"ami_corpus has wrong type {type(ami_corpus)}"
-            )
+            raise ValueError(f"ami_corpus has wrong type {type(ami_corpus)}")
 
         self.ami_corpus = ami_corpus
         self.file = Path(file)
@@ -510,12 +490,8 @@ def child_containers(self) -> List["AmiCorpusContainer"]:
         if self.ami_corpus and self.file and self.file.is_dir():
             child_nodes = self.ami_corpus._get_children(self.file)
             for child_node in child_nodes:
-                child_container = AmiCorpusContainer(
-                    self.ami_corpus, child_node
-                )
-                child_container.bib_type = (
-                    "" if child_node.is_dir() else "file"
-                )
+                child_container = AmiCorpusContainer(self.ami_corpus, child_node)
+                child_container.bib_type = "" if child_node.is_dir() else "file"
                 child_containers.append(child_container)
         return child_containers
 

corpus_module/query.py

@@ -88,15 +88,11 @@ def run_query_make_table_TUTORIAL(
             raise ValueError("No query_id given")
         query_id = query_id.strip()
         if " " in query_id:
-            raise ValueError(
-                f"no spaces allowed in query_id, found {query_id}"
-            )
+            raise ValueError(f"no spaces allowed in query_id, found {query_id}")
         self.query_id = query_id
 
         if indir is None or not Path(indir).exists():
-            logger.error(
-                f"input directory must exist {indir}"
-            )
+            logger.error(f"input directory must exist {indir}")
         self.indir = Path(indir)
         self.outfile = Path(outfile) if outfile else None
         if not self.outfile:
@@ -112,10 +108,7 @@ def run_query_make_table_TUTORIAL(
 
         # This would need to be implemented based on the search functionality
         # For now, we'll create a placeholder
-                    logger.info(
-                f"Running query: {query_id} with phrases: "
-                f"{self.phrases}"
-            )
+        logger.info(f"Running query: {query_id} with phrases: {self.phrases}")
 
         # Create a simple HTML table as placeholder
         from datatables_module import Datatables
@@ -135,11 +128,7 @@ def run_query_make_table_TUTORIAL(
 
         table_file = Path(outdir) / f"{self.query_id}_{TABLE_HITS_SUFFIX}"
         with open(table_file, "w", encoding="utf-8") as f:
-            f.write(
-                ET.tostring(
-                    htmlx, encoding="unicode", pretty_print=True
-                )
-            )
+            f.write(ET.tostring(htmlx, encoding="unicode", pretty_print=True))
 
         return htmlx, self.query_id
 
@@ -172,14 +161,12 @@ def get_hits_as_term_ref_p_tuple_list(
             List of (term, ref, para) tuples
         """
         if term_id_by_url is None:
-            logger.error(f"term_id_by_url is None")
+            logger.error("term_id_by_url is None")
             return None
 
         trp_list = []
         for ref in term_id_by_url.keys():
-            bits = ref.split("#")
-            file = bits[0]
-            idref = bits[1] if len(bits) > 1 else ""
+            # bits = ref.split("#")  # Unused, removed for F841
             term_p = term_id_by_url.get(ref)
             if term_p and len(term_p) >= 2:
                 term = term_p[0]
@@ -201,7 +188,7 @@ def _add_hits_to_table(
             term_ref_p_tuple_list: List of (term, ref, para) tuples
         """
         if term_ref_p_tuple_list is None:
-            logger.error(f"term_ref_p_tuple_list is None")
+            logger.error("term_ref_p_tuple_list is None")
             return
 
         for term, ref, p in term_ref_p_tuple_list:

corpus_module/search.py

@@ -73,7 +73,7 @@ def search_files_with_phrases_write_results(
         if outfile:
             outfile = Path(outfile)
             outfile.parent.mkdir(exist_ok=True, parents=True)
-            with open(outfile, "w", encoding="UTF-8") as f:
+            with open(outfile, "w", encoding="UTF-8"):
                 if debug:
                     print(f" hitdict {url_list_by_phrase_dict}")
                 cls.write_html_file(html1, outfile, debug=True)
@@ -103,14 +103,12 @@ def search_paras_with_id_and_create_dict(
             List of paragraph elements
         """
         infile_path = Path(infile)
-        assert infile_path.exists(), (
-            f"{infile} does not exist"
-        )
+        assert infile_path.exists(), f"{infile} does not exist"
 
         try:
             html_tree = ET.parse(str(infile), HTMLParser())
-        except Exception as e:
-            logger.error(f"Error parsing {infile}: {e}")
+        except Exception:
+            logger.error(f"Error parsing {infile}")
             return []
 
         paras = cls.find_paras_with_ids(html_tree, para_xpath=para_xpath)
@@ -121,9 +119,7 @@ def search_paras_with_id_and_create_dict(
             paras, phrases
         )
 
-        if para_id_by_phrase_dict is not None and len(
-            para_id_by_phrase_dict
-        ) > 0:
+        if para_id_by_phrase_dict is not None and len(para_id_by_phrase_dict) > 0:
             cls.add_hit_with_filename_and_para_id(
                 all_hits_dict,
                 url_list_by_phrase_dict,
@@ -206,18 +202,18 @@ def create_html_from_hit_dict(cls, hit_dict: Dict[str, List[str]]):
                 ss = "ipcc/"
                 try:
                     idx = a.text.index(ss)
-                except Exception as e:
-                    print(
-                        f"cannot find substring {ss} in {a.text}"
-                    )
+                except Exception:
+                    print(f"cannot find substring {ss} in {a.text}")
                     continue
-                a.text = a.text[idx + len(ss):]
+                a.text = a.text[idx + len(ss) :]
                 a.attrib["href"] = hit
 
         return html
 
     @classmethod
-    def find_paras_with_ids(cls, html_tree, para_xpath: Optional[str] = None) -> List[Any]:
+    def find_paras_with_ids(
+        cls, html_tree, para_xpath: Optional[str] = None
+    ) -> List[Any]:
         """
         Find paragraphs with IDs in HTML tree.
 
@@ -255,8 +251,8 @@ def create_search_results_para_phrase_dict(
     def create_html_with_empty_head_body():
         """Create basic HTML document structure."""
         html = ET.Element("html")
-        head = ET.SubElement(html, "head")
-        body = ET.SubElement(html, "body")
+        ET.SubElement(html, "head")
+        ET.SubElement(html, "body")
         return html
 
     @staticmethod
@@ -277,10 +273,10 @@ def write_html_file(htmlx, outfile: Union[str, Path], debug: bool = False):
         if debug:
             logger.info(f"writing HTML to {outfile}")
 
-        with open(outfile, "w", encoding="UTF-8") as f:
+        with open(outfile, "w", encoding="UTF-8") as _f:
             text = ET.tostring(
                 htmlx,
                 encoding="unicode",
                 pretty_print=True,
             )
-            f.write(text)
+            _f.write(text)

corpus_module/setup.py

@@ -51,9 +51,7 @@
             "requests>=2.25.0",
         ],
     },
-    keywords=(
-        "corpus, text-analysis, document-management, search, linguistics"
-    ),
+    keywords=("corpus, text-analysis, document-management, search, linguistics"),
     project_urls={
         "Bug Reports": "https://github.com/amilib/corpus-module/issues",
         "Source": "https://github.com/amilib/corpus-module",