pyeasyphd 0.1.2__py3-none-any.whl → 0.1.6__py3-none-any.whl

pyeasyphd/tools/py_run_bib_md_tex.py

@@ -18,27 +18,22 @@ class PyRunBibMdTex(BasicInput):
     """
 
     def __init__(
-        self, path_output: str, tex_md_flag: str = ".md", template_name: str = "paper", options: Dict[str, Any] = {}
+        self,
+        path_output: str,
+        tex_md_flag: str = ".md",
+        template_name: str = "paper",
+        options: Dict[str, Any] = {}
     ) -> None:
         """Initialize the PyRunBibMdTex instance.
 
-        Parameters
-        ----------
-        path_output : str
-            Output directory path for processed files
-        tex_md_flag : str, optional
-            Flag indicating whether to process as LaTeX (".tex") or Markdown (".md"),
-            by default ".md"
-        template_name : str, optional
-            Template type to use ("paper" or "beamer"), by default "paper"
-        options : Dict[str, Any], optional
-            Additional configuration options, by default {}
-
-        Raises
-        ------
-        AssertionError
-            If tex_md_flag is not ".tex" or ".md"
-            If template_name is not "paper" or "beamer"
+        Args:
+            path_output (str): Output directory path for processed files.
+            tex_md_flag (str, optional): Flag indicating whether to process as LaTeX (".tex") or Markdown (".md"). Defaults to ".md".
+            template_name (str, optional): Template type to use ("paper" or "beamer"). Defaults to "paper".
+            options (Dict[str, Any], optional): Additional configuration options. Defaults to {}.
+
+        Raises:
+            AssertionError: If tex_md_flag is not ".tex" or ".md" or if template_name is not "paper" or "beamer".
         """
         super().__init__(options)
 
@@ -48,10 +43,18 @@ class PyRunBibMdTex(BasicInput):
         assert self.template_name in ["paper", "beamer"], f"{template_name} must be `paper` or `beamer`."
         self.path_output = standard_path(path_output)
 
+        # Bib
+        # Path to bibliographic data, can be either a directory path or a specific file path
+        self.bib_path_or_file = options.get("bib_path_or_file", "")
+
+        # Figures
+        # Path to the figures directory (must be a directory path, not a file)
+        self.figures_directory = options.get("figures_directory", "")
+        self.shutil_figures = options.get("shutil_figures", True)
+
         # Configuration options
         self.generate_html = options.get("generate_html", False)
         self.generate_tex = options.get("generate_tex", True)
-        self.shutil_figures = options.get("shutil_figures", True)
 
         # Folder name configurations
         self.figure_folder_name = options.get("figure_folder_name", "fig")  # "" or "figs" or "main"
@@ -65,8 +68,8 @@ class PyRunBibMdTex(BasicInput):
         self.delete_original_bib_in_output_folder = options.get("delete_original_bib_in_output_folder", False)
 
         # Initialize helper classes
-        self._python_bib = PythonRunBib(self.full_json_c, self.full_json_j, self.options)
-        self._python_writer = PythonWriters(self.full_json_c, self.full_json_j, self.options)
+        self._python_bib = PythonRunBib(self.options)
+        self._python_writer = PythonWriters(self.options)
 
         self._python_md = PythonRunMd(self.options)
         self._python_tex = PythonRunTex(self.options)
@@ -76,19 +79,13 @@ class PyRunBibMdTex(BasicInput):
     ) -> Tuple[List[str], List[str]]:
         """Process a list of Markdown or LaTeX files.
 
-        Parameters
-        ----------
-        file_list_md_tex : List[str]
-            List of input file paths (Markdown or LaTeX)
-        output_prefix : str, optional
-            Prefix for output files, by default ""
-        output_level : str, optional
-            Output directory level ("previous", "current", or "next"), by default "next"
-
-        Returns
-        -------
-        Tuple[List[str], List[str]]
-            Tuple containing processed Markdown content and LaTeX content
+        Args:
+            file_list_md_tex (List[str]): List of input file paths (Markdown or LaTeX).
+            output_prefix (str, optional): Prefix for output files. Defaults to "".
+            output_level (str, optional): Output directory level ("previous", "current", or "next"). Defaults to "next".
+
+        Returns:
+            Tuple[List[str], List[str]]: Tuple containing processed Markdown content and LaTeX content.
         """
         file_list_md_tex = [f for f in file_list_md_tex if f.endswith(self.tex_md_flag)]
         data_list_list = [read_list(standard_path(f), "r") for f in file_list_md_tex]
@@ -101,7 +98,7 @@ class PyRunBibMdTex(BasicInput):
         data_list_md_tex = combine_content_in_list(data_list_list, ["\n"])
 
         content_md, content_tex = self.python_run_bib_md_tex(
-            output_prefix, data_list_md_tex, self.path_bibs, output_level
+            output_prefix, data_list_md_tex, self.bib_path_or_file, output_level
         )
         return content_md, content_tex
 
@@ -114,21 +111,14 @@ class PyRunBibMdTex(BasicInput):
     ) -> Tuple[List[str], List[str]]:
         """Process BibTeX, Markdown and LaTeX content.
 
-        Parameters
-        ----------
-        output_prefix : str
-            Prefix for output files
-        data_list_md_tex : List[str]
-            List of content lines (Markdown or LaTeX)
-        original_bib_data : Union[List[str], str, Library]
-            BibTeX data in various formats
-        output_level : str, optional
-            Output directory level ("previous", "current", or "next"), by default "next"
-
-        Returns
-        -------
-        Tuple[List[str], List[str]]
-            Tuple containing processed Markdown content and LaTeX content
+        Args:
+            output_prefix (str): Prefix for output files.
+            data_list_md_tex (List[str]): List of content lines (Markdown or LaTeX).
+            original_bib_data (Union[List[str], str, Library]): BibTeX data in various formats.
+            output_level (str, optional): Output directory level ("previous", "current", or "next"). Defaults to "next".
+
+        Returns:
+            Tuple[List[str], List[str]]: Tuple containing processed Markdown content and LaTeX content.
         """
         # Basic file names
         output_tex, output_md = output_prefix + ".tex", output_prefix + ".md"
@@ -168,26 +158,19 @@ class PyRunBibMdTex(BasicInput):
     ) -> Tuple[List[str], List[str]]:
         """Process BibTeX, Markdown and LaTeX content.
 
-        Parameters
-        ----------
-        output_md : str
-            Output Markdown filename
-        output_tex : str
-            Output LaTeX filename
-        data_list_md_tex : List[str]
-            List of content lines (Markdown or LaTeX)
-        original_bib_data : Union[List[str], str, Library]
-            BibTeX data in various formats
-
-        Returns
-        -------
-        Tuple[List[str], List[str]]
-            Tuple containing processed Markdown content and LaTeX content
+        Args:
+            output_md (str): Output Markdown filename.
+            output_tex (str): Output LaTeX filename.
+            data_list_md_tex (List[str]): List of content lines (Markdown or LaTeX).
+            original_bib_data (Union[List[str], str, Library]): BibTeX data in various formats.
+
+        Returns:
+            Tuple[List[str], List[str]]: Tuple containing processed Markdown content and LaTeX content.
         """
         # Copy figures if enabled
         if self.shutil_figures:
             figure_names = self.search_figure_names(data_list_md_tex)
-            self.shutil_copy_figures(self.figure_folder_name, self.path_figures, figure_names, self.path_output)
+            self.shutil_copy_figures(self.figure_folder_name, self.figures_directory, figure_names, self.path_output)
 
         # Extract citation keys from content
         key_in_md_tex = self.search_cite_keys(data_list_md_tex, self.tex_md_flag)
@@ -258,17 +241,12 @@ class PyRunBibMdTex(BasicInput):
     def search_figure_names(data_list: List[str], figure_postfixes: Optional[List[str]] = None) -> List[str]:
         """Search for figure filenames in content.
 
-        Parameters
-        ----------
-        data_list : List[str]
-            List of content lines to search
-        figure_postfixes : Optional[List[str]], optional
-            List of figure file extensions to look for, by default None
-
-        Returns
-        -------
-        List[str]
-            List of found figure filenames
+        Args:
+            data_list (List[str]): List of content lines to search.
+            figure_postfixes (Optional[List[str]], optional): List of figure file extensions to look for. Defaults to None.
+
+        Returns:
+            List[str]: List of found figure filenames.
         """
         if figure_postfixes is None:
             figure_postfixes = ["eps", "jpg", "png", "svg", "psd", "raw", "jpeg", "pdf"]
@@ -283,23 +261,17 @@ class PyRunBibMdTex(BasicInput):
     def shutil_copy_figures(fig_folder_name: str, path_fig: str, fig_names: List[str], path_output: str) -> None:
         """Copy figure files to output directory.
 
-        Parameters
-        ----------
-        fig_folder_name : str
-            Name of figures folder in output directory
-        path_fig : str
-            Source directory containing figures
-        fig_names : List[str]
-            List of figure filenames to copy
-        path_output : str
-            Output directory path
-
-        Returns
-        -------
-        None
+        Args:
+            fig_folder_name (str): Name of figures folder in output directory.
+            path_fig (str): Source directory containing figures.
+            fig_names (List[str]): List of figure filenames to copy.
+            path_output (str): Output directory path.
         """
+        if not fig_names:
+            return None
+
         if not os.path.exists(path_fig):
-            print(f"{path_fig} does not existed.")
+            print(f"The specified figure directory: {path_fig} does not exist.")
             return None
 
         file_list = []
@@ -308,6 +280,10 @@ class PyRunBibMdTex(BasicInput):
                 if name in fig_names:
                     file_list.append(os.path.join(root, name))
 
+        not_founded_figures = list(set([os.path.basename(f) for f in file_list]).intersection(set(fig_names)))
+        if not_founded_figures:
+            print(f"Figures: {', '.join(not_founded_figures)} could not be found.")
+
         for file in file_list:
             path_output_file = os.path.join(path_output, fig_folder_name, os.path.basename(file))
             p = os.path.dirname(path_output_file)
@@ -320,22 +296,16 @@ class PyRunBibMdTex(BasicInput):
     def search_cite_keys(data_list: List[str], tex_md_flag: str = ".tex") -> List[str]:
         r"""Extract citation keys from content according to their places.
 
-        Parameters
-        ----------
-        data_list : List[str]
-            List of content lines to search
-        tex_md_flag : str, optional
-            Flag indicating content format (".tex" or ".md"), by default ".tex"
-
-        Returns
-        -------
-        List[str]
-            List of found citation keys
-
-        Notes
-        -----
-        For LaTeX, searches for \\cite, \\citep, \\citet patterns
-        For Markdown, searches for [@key], @key; and ;@key] patterns
+        Args:
+            data_list (List[str]): List of content lines to search.
+            tex_md_flag (str, optional): Flag indicating content format (".tex" or ".md"). Defaults to ".tex".
+
+        Returns:
+            List[str]: List of found citation keys.
+
+        Note:
+            For LaTeX, searches for \\cite, \\citep, \\citet patterns.
+            For Markdown, searches for [@key], @key; and ;@key] patterns.
         """
         cite_key_list = []
         if tex_md_flag == ".tex":
@@ -360,14 +330,8 @@ class PyRunBibMdTex(BasicInput):
     def _cleanup_file(self, file_path: str) -> None:
         """Cleanup files and empty directories.
 
-        Parameters
-        ----------
-        file_path : str
-            Path to file to be removed
-
-        Returns
-        -------
-        None
+        Args:
+            file_path (str): Path to file to be removed.
         """
         if os.path.exists(file_path):
             os.remove(file_path)

pyeasyphd/tools/search/data.py

@@ -2,7 +2,11 @@ from typing import Any, Dict
 
 
 def obtain_search_keywords() -> Dict[str, Any]:
-    """Keywords."""
+    """Obtain search keywords dictionary.
+
+    Returns:
+        Dict[str, Any]: Dictionary containing categorized search keywords.
+    """
     _h_ = "(?:| |-)"  # hyphen
 
     evol = "evol(?:ution|utionary)"  # 'evol(?:ution|utionary|ve|ved|ving)'
@@ -62,10 +66,7 @@ def obtain_search_keywords() -> Dict[str, Any]:
         [moea_d],
         [nsga],
         [f"multi{_h_}objective optimization"],
-        [
-            [f"multi{_h_}objective", "optimization"],
-            [f"multi{_h_}objective optimization"],
-        ],
+        [[f"multi{_h_}objective", "optimization"], [f"multi{_h_}objective optimization"]],
         [[f"multi{_h_}objective"], ["optimization"]],
         [f"multi{_h_}model optimization"],
         [[f"multi{_h_}model", "optimization"], [f"multi{_h_}model optimization"]],
@@ -75,36 +76,15 @@ def obtain_search_keywords() -> Dict[str, Any]:
         [[f"many{_h_}objective"], ["optimization"]],
         [f"dynamic multi{_h_}objective"],
         [f"dynamic {evol} multi{_h_}objective"],
-        [
-            ["dynamic", f"multi{_h_}objective"],
-            [
-                f"dynamic multi{_h_}objective",
-                f"dynamic {evol} multi{_h_}objective"
-            ]
-        ],
+        [["dynamic", f"multi{_h_}objective"], [f"dynamic multi{_h_}objective", f"dynamic {evol} multi{_h_}objective"]],
         [f"dynamic multi{_h_}model"],
         [["dynamic", f"multi{_h_}model"], [f"dynamic multi{_h_}model"]],
         [f"dynamic many{_h_}objective"],
         [f"dynamic {evol} many{_h_}objective"],
-        [
-            ["dynamic", f"many{_h_}objective"],
-            [
-                f"dynamic many{_h_}objective",
-                f"dynamic {evol} many{_h_}objective",
-            ]
-        ],
+        [["dynamic", f"many{_h_}objective"], [f"dynamic many{_h_}objective", f"dynamic {evol} many{_h_}objective"]],
         ["dynamic", "optimization"],
         ["dynamic", network],
-        [
-            ["dynamic"],
-            [
-                f"multi{_h_}objective",
-                f"multi{_h_}model",
-                f"many{_h_}objective",
-                "optimization",
-                network,
-            ],
-        ],
+        [["dynamic"], [f"multi{_h_}objective", f"multi{_h_}model", f"many{_h_}objective", "optimization", network]],
         [f"{uncertain} optimization"],
         [[uncertain, "optimization"], [f"{uncertain} optimization"]],
         [[uncertain], ["optimization"]],
@@ -158,12 +138,7 @@ def obtain_search_keywords() -> Dict[str, Any]:
         ["active", "learning"],
         [
             ["supervised", "learning"],
-            [
-                f"semi{_h_}supervised",
-                f"self{_h_}supervised",
-                f"weakly{_h_}supervised",
-                "unsupervised",
-            ],
+            [f"semi{_h_}supervised", f"self{_h_}supervised", f"weakly{_h_}supervised", "unsupervised"],
         ],
         ["reinforcement", "learning", f"on{_h_}policy"],
         ["reinforcement", "learning", f"off{_h_}policy"],
@@ -174,15 +149,7 @@ def obtain_search_keywords() -> Dict[str, Any]:
         ["reinforcement", "learning", evol],
         [
             ["reinforcement", "learning"],
-            [
-                "offline",
-                f"on{_h_}policy",
-                f"off{_h_}policy",
-                f"model{_h_}based",
-                "deep",
-                "continual",
-                evol,
-            ],
+            ["offline", f"on{_h_}policy", f"off{_h_}policy", f"model{_h_}based", "deep", "continual", evol],
         ],
         ["policy", "search"],
         [["policy"], ["policy", "search"]],
@@ -295,10 +262,7 @@ def obtain_search_keywords() -> Dict[str, Any]:
         ["upper", bound],
         ["lower", bound],
         [[converg], [evol, "swarm", "colony", "genetic", analy]],
-        [
-            ["time"],
-            [evol, "swarm", "colony", "genetic", analy, "hitting", computation, run],
-        ],
+        [["time"], [evol, "swarm", "colony", "genetic", analy, "hitting", computation, run]],
         [[theor], [evol, "swarm", "colony", "genetic", analy]],
         [[bound], [evol, "swarm", "colony", "genetic", analy, "upper", "lower"]],
         [["complexity"], [evol, "swarm", "colony", "genetic", analy]],

pyeasyphd/tools/search/search_base.py

@@ -10,7 +10,16 @@ from .search_writers import WriteInitialResult, WriteSeparateResult
 
 
 def search_keywords_core(keywords_list_list: List[List[str]], library: Library, field: str) -> Tuple[Library, Library]:
-    """Search keywords in `field` such as `title` or `abstract` or `keywords`."""
+    """Search keywords in specified field such as title, abstract, or keywords.
+
+    Args:
+        keywords_list_list (List[List[str]]): List of keyword lists to search for.
+        library (Library): Bibliography library to search.
+        field (str): Field to search in (e.g., 'title', 'abstract', 'keywords').
+
+    Returns:
+        Tuple[Library, Library]: Tuple containing (matching_library, non_matching_library).
+    """
     search_library = []
     no_search_library = []
 
@@ -36,31 +45,34 @@ def search_keywords_core(keywords_list_list: List[List[str]], library: Library,
 
 
 class SearchInitialResult(BasicInput):
-    """Search initial result.
+    """Class for searching and processing initial results.
 
     Args:
-        options: dict
+        options (dict): Configuration options.
 
     Attributes:
-        options: dict
-
-        print_on_screen (bool = False): print on screen
-        deepcopy_library_for_every_field (bool = False): deepcopy library for every field
+        options (dict): Configuration options.
+        print_on_screen (bool): Whether to print results on screen. Defaults to False.
+        deepcopy_library_for_every_field (bool): Whether to deep copy library for every field. Defaults to False.
     """
 
     def __init__(self, options: dict) -> None:
-        self.options = options
+        """Initialize SearchInitialResult with configuration options.
+
+        Args:
+            options (dict): Configuration options.
+        """
         super().__init__(options)
 
         self.print_on_screen: bool = options.get("print_on_screen", False)
         self.deepcopy_library_for_every_field = options.get("deepcopy_library_for_every_field", False)
 
-        self._python_bib = PythonRunBib(self.full_json_c, self.full_json_j, options)
+        self._python_bib = PythonRunBib(options)
 
         _options = {}
         _options["empty_entry_cite_keys"] = True
         _options.update(self.options)
-        self._python_writer = PythonWriters(self.full_json_c, self.full_json_j, _options)
+        self._python_writer = PythonWriters(_options)
 
     def main(
         self,
@@ -73,7 +85,21 @@ class SearchInitialResult(BasicInput):
         output_prefix: str,
         path_separate: str,
     ) -> Tuple[List[str], Dict[str, List[List[str]]], Dict[str, int], Library]:
-        """Search."""
+        """Main search method for processing search results.
+
+        Args:
+            search_field_list (List[str]): List of fields to search.
+            path_initial (str): Path to initial directory.
+            library (Library): Bibliography library to search.
+            keywords_type (str): Type of keywords being searched.
+            keywords_list_list (List[List[str]]): List of keyword lists.
+            combine_keywords (str): Combined keywords string.
+            output_prefix (str): Prefix for output files.
+            path_separate (str): Path to separate directory.
+
+        Returns:
+            Tuple[List[str], Dict[str, List[List[str]]], Dict[str, int], Library]: Tuple containing error messages, field data, field numbers, and remaining library.
+        """
         error_pandoc_md_md, field_data_dict, no_search_library = [], {}, library
         field_number_dict: Dict[str, int] = {}