abstract-utilities 0.2.2.513__py3-none-any.whl → 0.2.2.583__py3-none-any.whl

abstract_utilities/file_utils (2)/src/pdf_utils.py

@@ -0,0 +1,300 @@
+from ..imports import *
+def if_none_return(obj: object, obj_2: object) -> object:
+    """
+    Return obj if obj_2 is None, otherwise return obj_2.
+    
+    Args:
+    obj (Any): Primary object to return.
+    obj_2 (Any): Secondary object to check.
+    
+    Returns:
+    Any: obj if obj_2 is None, else obj_2.
+    """
+    return obj if obj_2 is None else obj_2
+
+def write_pdf() -> PyPDF2.PdfWriter:
+    """
+    Return a new PDF writer object.
+    
+    Returns:
+    PyPDF2.PdfWriter: New PDF writer object.
+    """
+    return PyPDF2.PdfWriter()
+def read_pdf(file: str):
+    """
+    Read and return a PDF reader object from the provided file path.
+    
+    Args:
+    file (str): Path to the PDF file.
+    
+    Returns:
+    PyPDF2.PdfReader: PDF reader object.
+    """
+    return PyPDF2.PdfReader(file)
+def is_pdf_path(file: str):
+    """
+    Checks if a given file path corresponds to a PDF file.
+
+    Args:
+        file (str): A string representing the file path.
+
+    Returns:
+        bool: True if the file has a '.pdf' extension, False otherwise.
+    """
+    if is_file(file):
+        if get_ext(file) == '.pdf':
+            return True
+    return False
+
+def read_pdf(file: str):
+    """Read and return a PDF reader object from the provided file path."""
+    return PyPDF2.PdfReader(file)
+def get_pdf_obj(pdf_obj: Union[str, object]) -> object:
+    """
+    Processes and returns a PDF object. If provided with a file path to a PDF,
+    it reads and returns the PDF content as an object.
+
+    Args:
+        pdf_obj: Either a PDF file path or an existing PDF object.
+
+    Returns:
+        object: The PDF content as an object.
+    """
+    if is_str(pdf_obj):
+        if is_pdf_path(pdf_obj):
+            pdf_obj = read_pdf(pdf_obj)  # Assuming there's a function read_pdf() to read PDF content
+    return pdf_obj
+def get_separate_pages(pdf_reader, start_page:int=1, end_page:int=None):
+    """
+    Get specific pages from a PDF and return them as a new PDF object.
+
+    Args:
+        pdf_reader (object): The PDF reader object.
+        start_page (int, optional): The starting page number. Defaults to 1.
+        end_page (int, optional): The ending page number. Defaults to the last page.
+
+    Returns:
+        object: A new PDF writer object with the specified pages.
+    """
+    num_pages = get_pdf_pages(pdf_reader)
+    
+    # Handling default or out-of-bounds page values
+    if end_page is None or num_pages < end_page:
+        end_page = num_pages
+    elif num_pages < start_page:
+        return False
+    
+    pdf_writer = write_pdf()
+    
+    for page_num in range(num_pages):
+        if start_page <= page_num <= end_page:
+            pdf_writer.add_page(pdf_reader.pages[page_num])
+    return pdf_writer
+def is_pdf_path(file):
+    """
+    Check if the provided file path corresponds to a valid PDF file.
+
+    Args:
+        file (str): File path.
+
+    Returns:
+        bool: True if it's a valid PDF path, False otherwise.
+    """
+    if is_file(file) and get_ext(file).lower() == '.pdf':
+        return True
+    return False
+
+def get_pdf_pages(pdf_file):
+    """
+    Get the total number of pages in the PDF.
+
+    Args:
+        pdf_file (object/str): PDF reader object or path to a PDF file.
+
+    Returns:
+        int: Number of pages in the PDF.
+    """
+    pdf_file = get_pdf_obj(pdf_file)
+    try:
+        return len(pdf_file.pages)
+    except:
+        return False
+def save_pdf(output_file_path, pdf_writer):
+    """
+    Save a PDF writer object to a file.
+
+    Args:
+        output_file_path (str): Path to save the PDF.
+        pdf_writer (object): PDF writer object to save.
+    """
+    with open(output_file_path, 'wb') as output_file:
+        pdf_writer.write(output_file)
+def split_pdf(input_path: str, output_folder: Optional[str] = None, file_name: Optional[str] = None) -> List[str]:
+    """
+    Split a PDF file into separate files for each page.
+    
+    Args:
+        input_path (str): Path to the input PDF file.
+        output_folder (str, optional): Directory to save the split PDF files. Defaults to the directory of input_path.
+        file_name (str, optional): Base name for the output files. Defaults to the base name of input_path.
+        
+    Returns:
+        list: List of paths to the created split PDF files.
+    """
+    pdf_pages = []
+    file_name = get_file_name(input_path) if file_name is None else file_name
+    output_folder = if_none_return(get_directory(input_path), output_folder)  
+
+    print(f"Splitting PDF: {input_path}")
+    print(f"Output Folder: {output_folder}")
+    print(f"Using Filename: {file_name}")
+
+    with open(input_path, 'rb') as pdf_file:
+        pdf_reader = PyPDF2.PdfReader(pdf_file)
+        num_pages = len(pdf_reader.pages)  # Replace getNumPages() with len(pdf_reader.pages)
+
+        print(f"Number of pages in PDF: {num_pages}")
+
+        for page_num in range(num_pages):
+            pdf_writer = PyPDF2.PdfWriter()
+            pdf_writer.add_page(pdf_reader.pages[page_num])  # Use the pdf_writer instance you created
+
+            output_file_path = os.path.join(output_folder, f'{file_name}_page_{page_num + 1}.pdf')
+            output_img_path = os.path.join(output_folder, f'{file_name}_page_{page_num + 1}.png')
+            print(f"Writing to: {output_file_path}")
+            pdf_pages.append(output_file_path)
+            save_pdf(output_file_path,pdf_writer)
+            
+    return pdf_pages
+def pdf_to_img_list(pdf_list: List[str], output_folder: Optional[str] = None, file_name: Optional[str] = None, 
+                    paginate: bool = False, extension: str = "png") -> List[str]:
+    """
+    Convert a list of PDF files to images.
+
+    Args:
+        pdf_list (List[str]): List of paths to PDF files.
+        output_folder (str, optional): Directory to save the images. Defaults to PDF's directory.
+        file_name (str, optional): Base name for the images. Defaults to PDF's name.
+        paginate (bool): Whether to paginate the image names. Defaults to False.
+        extension (str): Extension for the image files. Defaults to "png".
+
+    Returns:
+        List[str]: List of paths to the created image files.
+    """
+    image_list=[]
+    file_name_start = file_name
+    for i, each in enumerate(pdf_list):
+        try:
+            images = convert_from_path(each)
+        except Exception as e:
+            print("An error occurred while converting the PDF:", e)
+        
+        if output_folder is None:
+            output_folder = get_directory(each)
+        if file_name_start is None:
+            file_name = get_file_name(each)
+        if paginate:
+            file_name=f"{file_name}_Page_{i}"
+        
+        for i, image in enumerate(images):
+            image_output_path = os.path.join(output_folder, f"{file_name}.{extension}")
+            image_list.append(image_output_path)
+            save_image(image=image, image_path=image_output_path, format=extension.upper())
+    return image_list
+def img_to_txt_list(img_list: List[str], output_folder: Optional[str] = None, file_name: Optional[str] = None, 
+                    paginate: bool = False, extension: str = "txt") -> List[str]:
+    """
+    Convert a list of image files to text.
+
+    Args:
+        img_list (List[str]): List of paths to image files.
+        output_folder (str, optional): Directory to save the text files. Defaults to image's directory.
+        file_name (str, optional): Base name for the text files. Defaults to image's name.
+        paginate (bool): Whether to paginate the text filenames. Defaults to False.
+        extension (str): Extension for the text files. Defaults to "txt".
+
+    Returns:
+        List[str]: List of paths to the created text files.
+    """
+    text_list = []
+    file_name_start = file_name
+    for i, each in enumerate(img_list):
+        if output_folder is None:
+            output_folder = get_directory(each)
+        if file_name_start is None:
+            file_name = get_file_name(each)
+        if paginate:
+            file_name=f"{file_name}_Page_{i}"
+        
+        text_output = image_to_text(each)
+        text_output_path = os.path.join(output_folder, f"{get_file_name(each)}.{extension}")
+        text_list.append(text_output_path)
+        write_to_file(filepath=text_output_path, contents=text_output)
+    return text_list
+def open_pdf_file(pdf_file_path: str) -> None:
+    """
+    Open a PDF file using the default associated program.
+    
+    Args:
+        pdf_file_path (str): Path to the PDF file to open.
+    """
+    try:
+        # Open the PDF file using the default associated program
+        cmd_input("open "+pdf_file_path)
+    except FileNotFoundError:
+        print("Error: The specified file does not exist.")
+    except Exception as e:
+        print("Error:", e)
+    # use it before writing to a file
+
+
+def get_pdfs_in_directory(directory: str) -> List[str]:
+    """
+    Get a list of PDF filenames in a given directory.
+    
+    Args:
+        directory (str): Path to the directory.
+        
+    Returns:
+        list: List of PDF filenames in the directory.
+    """
+    pdfs = []
+    for filename in os.listdir(directory):
+        if is_pdf_path(filename):
+            pdfs.append(filename)
+    return pdfs
+
+def get_all_pdf_in_directory(file_directory: Optional[str] = None) -> List[str]:
+    """
+    Get a list of complete paths to PDF files in a given directory.
+    
+    Args:
+        file_directory (str, optional): Path to the directory. 
+        
+    Returns:
+        list: List of paths to PDF files in the directory.
+    """
+    pdfs=[]
+    for filename in sorted(os.listdir(file_directory)):
+        if is_pdf_path(filename):
+            pdf_path = os.path.join(file_directory, filename)
+            if is_file(pdf_path):
+                pdfs.append(pdf_path)
+    return pdfs
+
+def collate_pdfs(pdf_list: List[str], output_pdf_path: str) -> None:
+    """
+    Merge multiple PDF files into a single PDF.
+    
+    Args:
+        pdf_list (list): List of paths to PDF files to be merged.
+        output_pdf_path (str): Path to save the merged PDF.
+    """
+    pdf_writer = PyPDF2.PdfWriter()
+    for file_path in pdf_list:
+        with open(file_path, 'rb') as pdf_file:
+            pdf_reader = PyPDF2.PdfReader(pdf_file)
+            for page_num in range(len(pdf_reader.pages)):
+                pdf_writer.add_page(pdf_reader.pages[page_num])
+    save_pdf(output_file_path, pdf_writer)
+

abstract_utilities/import_utils/circular_import_finder.py

@@ -0,0 +1,222 @@
+from abstract_utilities import *
+from collections import defaultdict
+def clean_line(line):
+    return eatAll(line,[' ','','\t','\n'])
+def is_from_line_group(line):
+    if line and line.startswith(FROM_TAG) and IMPORT_TAG in line and '(' in line:
+        import_spl = line.split(IMPORT_TAG)[-1]
+        import_spl_clean = clean_line(line)
+        if not import_spl_clean.endswith(')'):
+            return True
+    return False
+def clean_imports(text=None,file_path=None,import_pkg_js=None,fill_nulines=False):
+    if text and os.path.isfile(text):
+        file_path = text
+        input(file_path)
+        text = read_from_file(file_path)    
+    if not import_pkg_js:
+        import_pkg_js = get_all_imports(text=text,file_path=file_path)
+    import_pkg_js = ensure_import_pkg_js(import_pkg_js,file_path=file_path)
+    nu_lines = import_pkg_js["context"]["nulines"]
+    for pkg,values in import_pkg_js.items():
+        comments = []
+        if pkg not in ["context"]: 
+            
+            imports = values.get('imports')
+            for i,imp in enumerate(imports):
+                if '#' in imp:
+                    imp_spl = imp.split('#')
+                    comments.append(imp_spl[-1])
+                    imports[i] = clean_line(imp_spl[0])
+            imports = list(set(imports))   
+            if '*' in imports:
+                imports="*"
+            else:
+                imports=','.join(imports)
+                if comments:
+                    comments=','.join(comments)
+                    imports+=f" #{comments}"
+            import_pkg_js[pkg]["imports"]=imports
+            if fill_nulines:
+                line = values.get('line')
+                if len(nu_lines) >= line:
+                    nu_lines[line] += imports
+    return import_pkg_js
+def get_all_imports(text=None,file_path=None,import_pkg_js=None):
+    if text and os.path.isfile(text):
+        
+        try:
+            text = read_from_file(text)    
+        except:
+            pass
+        file_path = text
+    text = get_text_or_read(text=text,file_path=file_path)
+    lines = text.split('\n')
+    cleaned_import_list=[]
+    nu_lines = []
+    is_from_group = False
+    import_pkg_js = ensure_import_pkg_js(import_pkg_js,file_path=file_path)
+    for line in lines:
+        if line.startswith(IMPORT_TAG) and ' from ' not in line:
+            cleaned_import_list = get_cleaned_import_list(line)
+            import_pkg_js = add_imports_to_import_pkg_js("import",cleaned_import_list,import_pkg_js=import_pkg_js)
+        else:
+            if is_from_group:
+                import_pkg=is_from_group
+                line = clean_line(line)
+                if line.endswith(')'):
+                   is_from_group=False
+                   line=line[:-1]
+                imports_from_import_pkg = clean_imports(line)
+                import_pkg_js = add_imports_to_import_pkg_js(import_pkg,imports_from_import_pkg,import_pkg_js=import_pkg_js)
+                
+            else:
+                import_pkg_js=update_import_pkg_js(line,import_pkg_js=import_pkg_js)
+            if is_from_line_group(line) and is_from_group == False:
+                is_from_group=get_import_pkg(line)
+    return import_pkg_js
+def get_path_or_init(pkg_info):
+    root_dirname = pkg_info.get("root_dirname")
+    pkg = pkg_info.get("pkg")
+    rel_path = pkg.replace('.','/')
+    dirname = os.path.dirname(root_dirname)
+    pkg_path = os.path.join(dirname,rel_path)
+    pkg_py_path = f"{pkg_path}.py"
+    if os.path.isfile(pkg_py_path):
+        return pkg_py_path
+    pkg_init_path = os.path.join(pkg_path,'__init__.py')
+    if os.path.isdir(pkg_path):
+        if os.path.isfile(pkg_init_path):
+            return pkg_init_path
+    #input(f"nnot found == {pkg_info}")
+def get_dot_fro_line(line,dirname=None,file_path=None,get_info=False):
+    info_js = {"nuline":line,"og_line":line,"pkg":line,"dirname":dirname,"file_path":file_path,"root_dirname":None,"local":False}
+    if dirname and is_file(dirname):
+        file_path=dirname
+        dirname = os.path.dirname(dirname)
+        info_js["file_path"]=file_path
+        info_js["dirname"]=dirname
+    from_line = line.split(FROM_TAG)[-1]
+    dot_fro = ""
+    for char in from_line:
+        if  char != '.':
+            pkg = f"{dot_fro}{eatAll(from_line,'.')}"
+            nuline=f"from {pkg}"
+            info_js["nuline"]=nuline
+            info_js["pkg"]=pkg
+            break
+        if dirname:
+            info_js["root_dirname"]=dirname
+            dirbase = os.path.basename(dirname)
+            dirname = os.path.dirname(dirname)
+            
+            dot_fro = f"{dirbase}.{dot_fro}"
+    if get_info:
+        if dot_fro and os.path.isdir(info_js["root_dirname"]):
+            info_js["local"]=True
+            info_js["pkg_path"]=get_path_or_init(info_js)
+        return info_js
+    return line
+def get_top_level_imp(line,dirname=None):
+    imp = get_dot_fro_line(line,dirname)
+    return imp.split('.')[0]
+def return_local_imps(file_path):
+    local_imps = []
+    dirname = os.path.dirname(file_path)
+    imports_js = get_all_imports(file_path)
+    for pkg,imps in imports_js.items():
+        if pkg not in ['context','nulines']:
+           full_imp_info = get_dot_fro_line(pkg,dirname,file_path=file_path,get_info=True)
+           if full_imp_info.get("local") == True:
+               local_imps.append(full_imp_info)
+    return local_imps
+def get_all_pkg_paths(file_path):
+    pkg_paths = []
+    local_imps = return_local_imps(file_path)
+    for local_imp in local_imps:
+        curr_file_path = local_imp.get('file_path')
+        pkg_path = local_imp.get('pkg_path')
+        if pkg_path != None:
+            pkg_paths.append(pkg_path)
+    return pkg_paths
+def get_cir_dir(pkg_path):
+    dirname = os.path.dirname(pkg_path)
+    dirbase = os.path.basename(dirname)
+    while True:
+        if dirname == "/home/flerb/Documents/pythonTools/modules/src/modules/abstract_utilities/src/abstract_utilities":
+            break
+        dirbase = os.path.basename(dirname)
+        dirname = os.path.dirname(dirname)
+    #input(f"{dirbase} is circular")
+    return dirbase 
+def is_circular(pkg_path):
+    pkg_paths = get_all_pkg_paths(pkg_path)
+    if pkg_path in pkg_paths:
+        return pkg_path
+def are_circular(pkg_path,cir_dirs = None):
+    cir_dirs = cir_dirs or []
+    pkg_path = is_circular(pkg_path)
+    if pkg_path:
+        if pkg_path not in cir_dirs:
+            cir_dirs.append(pkg_path)
+    return cir_dirs
+
+
+def build_dependency_graph(main_directory):
+    """Map each file to all local imports (by resolved pkg_path)."""
+    graph = defaultdict(list)
+    dirs, all_local_scripts = get_files_and_dirs(
+        main_directory,
+        allowed_exts='.py',
+        exclude_dirs=['depriciate', 'junk'],
+        files_only=True
+    )
+    for file_path in all_local_scripts:
+        deps = get_all_pkg_paths(file_path)
+        for dep in deps:
+            if dep and os.path.isfile(dep):
+                graph[file_path].append(dep)
+    return graph
+
+
+def find_circular_chains(graph):
+    """Detect circular imports and return their full dependency paths."""
+    visited, cycles = set(), []
+
+    def dfs(node, path):
+        visited.add(node)
+        path.append(node)
+        for dep in graph.get(node, []):
+            if dep not in path:
+                dfs(dep, path.copy())
+            else:
+                # Found a circular import
+                cycle_start = path.index(dep)
+                cycle = path[cycle_start:] + [dep]
+                if cycle not in cycles:
+                    cycles.append(cycle)
+        return
+
+    for start in graph:
+        dfs(start, [])
+    return cycles
+
+
+def explain_circular_imports(cycles):
+    """Pretty-print circular import chains with file names and import lines."""
+    for i, cycle in enumerate(cycles, 1):
+        print(f"\n🔁 Circular import {i}:")
+        for j in range(len(cycle) - 1):
+            src, dst = cycle[j], cycle[j + 1]
+            print(f"  {os.path.basename(src)}  →  {os.path.basename(dst)}")
+        print(f"  ^ back to {os.path.basename(cycle[0])}")
+main_directory = "/home/flerb/Documents/pythonTools/modules/src/modules/abstract_utilities/src/abstract_utilities"
+
+graph = build_dependency_graph(main_directory)
+cycles = find_circular_chains(graph)
+
+if not cycles:
+    print("✅ No circular imports found.")
+else:
+    print(f"❌ Found {len(cycles)} circular import(s).")
+    explain_circular_imports(cycles)

abstract_utilities/import_utils/circular_import_finder2.py

@@ -0,0 +1,118 @@
+from abstract_utilities import *
+import os
+from collections import defaultdict
+
+def get_path_or_init(pkg_info):
+    root_dirname = pkg_info.get("root_dirname")
+    pkg = pkg_info.get("pkg")
+    rel_path = pkg.replace('.', '/')
+    dirname = os.path.dirname(root_dirname)
+    pkg_path = os.path.join(dirname, rel_path)
+    pkg_py_path = f"{pkg_path}.py"
+    if os.path.isfile(pkg_py_path):
+        return pkg_py_path
+    pkg_init_path = os.path.join(pkg_path, '__init__.py')
+    if os.path.isdir(pkg_path) and os.path.isfile(pkg_init_path):
+        return pkg_init_path
+    # optional: silence instead of blocking input()
+    print(f"⚠️ not found == {pkg_info}")
+    return None
+
+
+def get_dot_fro_line(line, dirname=None, file_path=None, get_info=False):
+    info_js = {"nuline": line, "og_line": line, "pkg": line, "dirname": dirname,
+               "file_path": file_path, "root_dirname": None, "local": False}
+    if dirname and is_file(dirname):
+        file_path = dirname
+        dirname = os.path.dirname(dirname)
+        info_js["file_path"] = file_path
+        info_js["dirname"] = dirname
+
+    from_line = line.split(FROM_TAG)[-1]
+    dot_fro = ""
+    for char in from_line:
+        if char != '.':
+            pkg = f"{dot_fro}{eatAll(from_line, '.')}"
+            nuline = f"from {pkg}"
+            info_js["nuline"] = nuline
+            info_js["pkg"] = pkg
+            break
+        if dirname:
+            info_js["root_dirname"] = dirname
+            dirbase = os.path.basename(dirname)
+            dirname = os.path.dirname(dirname)
+            dot_fro = f"{dirbase}.{dot_fro}"
+
+    if get_info:
+        if dot_fro and os.path.isdir(info_js.get("root_dirname") or ""):
+            info_js["local"] = True
+            info_js["pkg_path"] = get_path_or_init(info_js)
+        return info_js
+    return line
+
+
+def return_local_imps(file_path):
+    local_imps = []
+    dirname = os.path.dirname(file_path)
+    imports_js = get_all_imports(file_path)
+    for pkg, imps in imports_js.items():
+        if pkg not in ['context', 'nulines']:
+            full_imp_info = get_dot_fro_line(pkg, dirname, file_path=file_path, get_info=True)
+            if full_imp_info.get("local"):
+                local_imps.append(full_imp_info)
+    return local_imps
+
+
+def get_all_pkg_paths(file_path):
+    pkg_paths = []
+    local_imps = return_local_imps(file_path)
+    for local_imp in local_imps:
+        pkg_path = local_imp.get('pkg_path')
+        if pkg_path:
+            pkg_paths.append(pkg_path)
+    return pkg_paths
+
+
+# --- NEW: Build dependency graph and detect circular imports ---
+
+def build_graph(main_directory):
+    dirs, all_local_scripts = get_files_and_dirs(main_directory, allowd_exts='.py', files_only=True)
+    graph = defaultdict(set)
+    for file_path in all_local_scripts:
+        deps = get_all_pkg_paths(file_path)
+        for dep in deps:
+            if dep:  # only valid files
+                graph[file_path].add(dep)
+    return graph
+
+
+def find_cycles(graph):
+    visited, stack, cycles = set(), [], []
+
+    def dfs(node, path):
+        visited.add(node)
+        path.append(node)
+        for dep in graph.get(node, []):
+            if dep not in visited:
+                dfs(dep, path.copy())
+            elif dep in path:
+                cycle_start = path.index(dep)
+                cycles.append(path[cycle_start:] + [dep])
+
+    for node in graph:
+        if node not in visited:
+            dfs(node, [])
+    return cycles
+
+
+if __name__ == "__main__":
+    main_directory = "/home/flerb/Documents/pythonTools/modules/src/modules/abstract_utilities/src/abstract_utilities"
+    graph = build_graph(main_directory)
+    cycles = find_cycles(graph)
+
+    if not cycles:
+        print("✅ No circular imports found.")
+    else:
+        print("❌ Circular imports detected:")
+        for cycle in cycles:
+            print(" → ".join(cycle))

abstract_utilities/import_utils/imports/module_imports.py

@@ -1,6 +1,8 @@
 from ...read_write_utils import read_from_file,write_to_file,get_text_or_read
 from ...string_utils import eatAll,eatInner,eatElse,clean_line
-from ...class_utils import get_caller_path
+from ...class_utils import get_caller_path,get_caller_dir,if_none_default,get_initial_caller_dir
 from ...list_utils import make_list
 from ...path_utils import get_file_parts
 from ...type_utils  import is_number,make_list
+from ...file_utils  import collect_filepaths,collect_globs
+from ...directory_utils import get_shortest_path,get_common_root