abstract-utilities 0.2.2.444__tar.gz → 0.2.2.490__tar.gz

{abstract_utilities-0.2.2.444 → abstract_utilities-0.2.2.490}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: abstract_utilities
-Version: 0.2.2.444
+Version: 0.2.2.490
 Summary: abstract_utilities is a collection of utility modules providing a variety of functions to aid in tasks such as data comparison, list manipulation, JSON handling, string manipulation, mathematical computations, and time operations.
 Home-page: https://github.com/AbstractEndeavors/abstract_utilities
 Author: putkoff

{abstract_utilities-0.2.2.444 → abstract_utilities-0.2.2.490}/setup.py

@@ -4,7 +4,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
     long_description = fh.read()
 setuptools.setup(
     name='abstract_utilities',
-    version='0.2.2.444',
+    version='0.2.2.490',
     author='putkoff',
     author_email='partners@abstractendeavors.com',
     description='abstract_utilities is a collection of utility modules providing a variety of functions to aid in tasks such as data comparison, list manipulation, JSON handling, string manipulation, mathematical computations, and time operations.',

{abstract_utilities-0.2.2.444 → abstract_utilities-0.2.2.490}/src/abstract_utilities/__init__.py

@@ -116,9 +116,10 @@ from .parse_utils import (num_tokens_from_string,
 
 from .log_utils import get_caller_info,get_logFile,print_or_log,get_json_call_response,initialize_call_log
 from .error_utils import try_func
-from .class_utils import alias,get_class_inputs,get_set_attr
 from .ssh_utils import *
 from .env_utils import *
 from .path_utils import *
 from .file_utils import *
 from .file_utils import call_for_all_tabs
+from .string_utils import *
+from .class_utils import alias,get_class_inputs,get_set_attr,get_caller_path,get_caller_dir

{abstract_utilities-0.2.2.444 → abstract_utilities-0.2.2.490}/src/abstract_utilities/class_utils.py

@@ -405,4 +405,3 @@ def get_caller_dir(i: Optional[int] = None) -> str:
     abspath = get_caller_path(depth + 1)
     return os.path.dirname(abspath)
 
-

{abstract_utilities-0.2.2.444 → abstract_utilities-0.2.2.490}/src/abstract_utilities/file_utils/file_utils/__init__.py

@@ -4,3 +4,5 @@ from .filter_params import *
 from .map_utils import *
 from .pdf_utils import *
 from .file_reader import *
+from .find_collect import *
+from .type_checks import *

{abstract_utilities-0.2.2.444 → abstract_utilities-0.2.2.490}/src/abstract_utilities/file_utils/file_utils/file_utils.py

@@ -1,7 +1,7 @@
-from pathlib import Path
-from typing import *
-import fnmatch, os, glob
+
 from .filter_params import *
+from .imports import *
+
 ##from abstract_utilities import make_list,get_media_exts, is_media_type
 def get_allowed_predicate(allowed=None):
     if allowed != False:

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/file_utils/find_collect.py

@@ -0,0 +1,154 @@
+from .imports import *
+from .filter_params import *
+from .file_filters import enumerate_source_files
+
+
+def check_path_type(
+    path: str,
+    user: Optional[str] = None,
+    host: Optional[str] = None,
+    user_as_host: Optional[str] = None,
+    use_shell: bool = False
+) -> Literal["file", "directory", "missing", "unknown"]:
+    """
+    Determine whether a given path is a file, directory, or missing.
+    Works locally or remotely (via SSH).
+
+    Args:
+        path: The path to check.
+        user, host, user_as_host: SSH parameters if remote.
+        use_shell: Force shell test instead of Python os.path.
+    Returns:
+        One of: 'file', 'directory', 'missing', or 'unknown'
+    """
+
+    # --- remote check if user/host is given ---
+    if user_as_host or (user and host):
+        remote_target = user_as_host or f"{user}@{host}"
+        cmd = f"if [ -f '{path}' ]; then echo file; elif [ -d '{path}' ]; then echo directory; else echo missing; fi"
+        try:
+            result = subprocess.check_output(
+                ["ssh", remote_target, cmd],
+                stderr=subprocess.DEVNULL,
+                text=True,
+                timeout=5
+            ).strip()
+            return result if result in ("file", "directory", "missing") else "unknown"
+        except Exception:
+            return "unknown"
+
+    # --- local check ---
+    if not use_shell:
+        if os.path.isfile(path):
+            return "file"
+        elif os.path.isdir(path):
+            return "directory"
+        elif not os.path.exists(path):
+            return "missing"
+        return "unknown"
+    else:
+        # fallback using shell tests (useful for sandboxed contexts)
+        cmd = f"if [ -f '{path}' ]; then echo file; elif [ -d '{path}' ]; then echo directory; else echo missing; fi"
+        try:
+            output = subprocess.check_output(
+                cmd, shell=True, stderr=subprocess.DEVNULL, text=True
+            ).strip()
+            return output if output in ("file", "directory", "missing") else "unknown"
+        except Exception:
+            return "unknown"
+
+
+
+
+def get_find_cmd(
+    directory: str,
+    *,
+    mindepth: Optional[int] = None,
+    maxdepth: Optional[int] = None,
+    depth: Optional[int] = None,
+    file_type: Optional[str] = None,  # 'f' or 'd'
+    name: Optional[str] = None,
+    size: Optional[str] = None,
+    mtime: Optional[str] = None,
+    perm: Optional[str] = None,
+    user: Optional[str] = None,
+    **kwargs
+) -> str:
+    """Constructs a Unix `find` command string from keyword args."""
+    cmd = [f"find {directory}"]
+
+    if depth is not None:
+        cmd += [f"-mindepth {depth}", f"-maxdepth {depth}"]
+    else:
+        if mindepth is not None:
+            cmd.append(f"-mindepth {mindepth}")
+        if maxdepth is not None:
+            cmd.append(f"-maxdepth {maxdepth}")
+
+    if file_type in ("f", "d"):
+        cmd.append(f"-type {file_type}")
+    if name:
+        cmd.append(f"-name '{name}'")
+    if size:
+        cmd.append(f"-size {size}")
+    if mtime:
+        cmd.append(f"-mtime {mtime}")
+    if perm:
+        cmd.append(f"-perm {perm}")
+    if user:
+        cmd.append(f"-user {user}")
+
+    return " ".join(cmd)
+
+
+def collect_globs(
+    directory: str,
+    cfg: Optional["ScanConfig"] = None,
+    *,
+    exts: Optional[Set[str]] = None,
+    patterns: Optional[List[str]] = None,
+    mindepth: Optional[int] = None,
+    maxdepth: Optional[int] = None,
+    depth: Optional[int] = None,
+    file_type: Optional[str] = None,
+    user_at_host: Optional[str] = None,
+    add: bool = False,
+    **kwargs
+) -> List[str]:
+    """
+    Collect file or directory paths using either:
+      - local recursive logic (rglob)
+      - or remote shell call (find via run_cmd)
+    """
+    cfg = cfg or define_defaults(add=add)
+    directory = str(directory)
+    exts = ensure_exts(exts)
+    patterns = ensure_patterns(patterns)
+
+    # Remote path via SSH
+    if user_at_host:
+        find_cmd = get_find_cmd(
+            directory,
+            mindepth=mindepth,
+            maxdepth=maxdepth,
+            depth=depth,
+            file_type=file_type,
+            **{k: v for k, v in kwargs.items() if v},
+        )
+        return run_cmd(find_cmd, user_at_host=user_at_host)
+
+    # Local path (Python-native walk)
+    root = Path(directory)
+    results = []
+    for p in root.rglob("*"):
+        if file_type == "f" and not p.is_file():
+            continue
+        if file_type == "d" and not p.is_dir():
+            continue
+        if exts and p.suffix.lower() not in exts:
+            continue
+        if patterns and not any(p.match(pat) for pat in patterns):
+            continue
+        results.append(str(p.resolve()))
+
+    return sorted(results)

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/file_utils/imports/__init__.py

@@ -0,0 +1,3 @@
+from .constants import *
+from .imports import *
+from ..imports import *

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/file_utils/imports/imports.py

@@ -0,0 +1,39 @@
+# ============================================================
+# abstract_utilities/imports/imports.py
+# Global imports hub — everything imported here will be
+# automatically available to any module that does:
+#     from ..imports import *
+# ============================================================
+# ---- Core standard library modules -------------------------
+import os, sys, re, shlex, glob, platform, textwrap, subprocess, inspect, json, time
+import tempfile, shutil, logging, pathlib, fnmatch, importlib, importlib.util, types
+from pathlib import Path
+from datetime import datetime
+from types import ModuleType
+
+# ---- Dataclasses and typing --------------------------------
+from dataclasses import dataclass, field
+from typing import (
+    Any, Optional, List, Dict, Set, Tuple,
+    Iterable, Callable, Literal, Union, TypeVar
+)
+
+# ---- Common 3rd-party dependencies --------------------------
+import pandas as pd
+import geopandas as gpd
+import pytesseract
+import pdfplumber
+import PyPDF2
+import ezodf
+from pdf2image import convert_from_path
+from werkzeug.utils import secure_filename
+from werkzeug.datastructures import FileStorage
+
+# ---- Helpers ------------------------------------------------
+import textwrap as tw
+from pprint import pprint
+
+# ============================================================
+# AUTO-EXPORT ALL NON-PRIVATE NAMES
+# ============================================================
+__all__ = [name for name in globals() if not name.startswith("_")]

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/file_utils/imports/module_imports.py

@@ -0,0 +1,14 @@
+from .imports import *
+from ....string_clean import eatAll
+from ....list_utils import make_list
+from ....type_utils import get_media_exts, is_media_type, MIME_TYPES, is_str
+from ....ssh_utils import *
+from ....env_utils import *
+from ....read_write_utils import *
+from ....abstract_classes import SingletonMeta
+from ....string_utils import get_from_kwargs
+from ....abstract_classes import run_pruned_func
+from ....class_utils import get_caller, get_caller_path, get_caller_dir
+
+
+__all__ = [name for name in globals() if not name.startswith("_")]

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/file_utils/type_checks.py

@@ -0,0 +1,92 @@
+from .imports import *
+
+def get_user_pass_host_key(**kwargs):
+    args = ['password','user_at_host','host','key','user']
+    kwargs['del_kwarg']=kwargs.get('del_kwarg',False)
+    values,kwargs = get_from_kwargs(*args,**kwargs)
+    return values
+
+# --- Base remote checker -----------------------------------------------------
+def _remote_test(path: str, test_flag: str, timeout: int = 5,*args, **kwargs) -> bool:
+    """
+    Run a remote shell test (e.g. -f, -d) via SSH.
+    Returns True if test succeeds, False otherwise.
+    """
+    try:
+        kwargs['cmd']=f"[ {test_flag} {shlex.quote(path)} ] && echo 1 || echo 0"
+        kwargs['text']=True
+        kwargs['timeout']=timeout
+        kwargs['stderr']=subprocess.DEVNULL
+        result = run_pruned_func(run_cmd,**kwargs)
+        return result.strip() == "1"
+    except Exception:
+        return False
+
+
+# --- Individual path checks --------------------------------------------------
+def is_remote_file(path: str,*args, **kwargs) -> bool:
+    """True if remote path is a file."""
+    return _remote_test(path, "-f", **kwargs)
+
+
+def is_remote_dir(path: str,*args, **kwargs) -> bool:
+    """True if remote path is a directory."""
+    return _remote_test(path, "-d", **kwargs)
+
+
+def is_local_file(path: str) -> bool:
+    """True if local path is a file."""
+    return os.path.isfile(path)
+
+
+def is_local_dir(path: str) -> bool:
+    """True if local path is a directory."""
+    return os.path.isdir(path)
+
+
+# --- Unified interface -------------------------------------------------------
+
+def is_file(path: str,*args,**kwargs) -> bool:
+    """Determine if path is a file (works local or remote)."""
+    if get_user_pass_host_key(**kwargs):
+        return is_remote_file(path, **kwargs)
+    return is_local_file(path)
+
+
+def is_dir(path: str, *args,**kwargs) -> bool:
+    """Determine if path is a directory (works local or remote)."""
+    if get_user_pass_host_key(**kwargs):
+        return is_remote_dir(path, **kwargs)
+    return is_local_dir(path)
+
+def is_exists(path: str, *args,**kwargs) -> bool:
+    if is_file(path,**kwargs):
+        return True
+    if is_dir(path,**kwargs):
+        return True
+    return False
+# --- Optional: keep your original all-in-one wrapper ------------------------
+def check_path_type(
+    path: str,
+    *args,
+    **kwargs
+) -> str:
+    """
+    Return 'file', 'directory', 'missing', or 'unknown'.
+    Uses isolated is_file/is_dir functions.
+    """
+    if get_user_pass_host_key(**kwargs):
+        if is_remote_file(path,**kwargs):
+            return "file"
+        elif is_remote_dir(path,**kwargs):
+            return "directory"
+        else:
+            return "missing"
+    else:
+        if os.path.isfile(path):
+            return "file"
+        elif os.path.isdir(path):
+            return "directory"
+        elif not os.path.exists(path):
+            return "missing"
+        return "unknown"

{abstract_utilities-0.2.2.444 → abstract_utilities-0.2.2.490}/src/abstract_utilities/file_utils/imports/__init__.py

@@ -1,5 +1,4 @@
 from .constants import *
-from .imports import *
 from .module_imports import *
 from .classes import *
-from .file_functions import *
+from .imports import *

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/imports/clean_imps.py

@@ -0,0 +1,158 @@
+from abstract_utilities import read_from_file, eatAll
+import os, sys, re, inspect
+from typing import *
+
+# ============================================================
+# Constants
+# ============================================================
+import_tag = 'import '
+from_tag = 'from '
+
+# ============================================================
+# Helpers
+# ============================================================
+def get_caller_path(i=None):
+    i = i or 1
+    frame = inspect.stack()[i]
+    return os.path.abspath(frame.filename)
+
+def make_list(obj: any) -> list:
+    if isinstance(obj, str) and ',' in obj:
+        obj = obj.split(',')
+    if isinstance(obj, (set, tuple)):
+        return list(obj)
+    if isinstance(obj, list):
+        return obj
+    return [obj]
+
+def eatElse(stringObj, chars=None):
+    chars = make_list(chars or []) + list('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_')
+    while stringObj:
+        if stringObj and stringObj[0] not in chars:
+            stringObj = stringObj[1:]
+            continue
+        if stringObj and stringObj[-1] not in chars:
+            stringObj = stringObj[:-1]
+            continue
+        break
+    return stringObj
+
+def clean_line(line):
+    return eatAll(line, [' ', '', '\t', '\n'])
+
+def is_line_import(line):
+    return bool(line and line.startswith(import_tag) and 'from ' not in line)
+
+def is_line_from_import(line):
+    return bool(line and line.startswith(from_tag) and ' import ' in line)
+
+def is_from_group_start(line):
+    return bool(line and line.startswith(from_tag) and 'import' in line and '(' in line and not line.rstrip().endswith(')'))
+
+def is_from_group_end(line):
+    return bool(line and ')' in line)
+
+def clean_imports(imports):
+    if isinstance(imports, str):
+        imports = imports.split(',')
+    return [eatElse(imp.strip()) for imp in imports if imp.strip()]
+
+# ============================================================
+# Combine lone import statements
+# ============================================================
+def combine_lone_imports(text=None, file_path=None):
+    text = text or ''
+    if file_path and os.path.isfile(file_path):
+        text += read_from_file(file_path)
+    lines = text.split('\n')
+
+    cleaned_import_list = []
+    nu_lines = []
+    j = None
+
+    for i, line in enumerate(lines):
+        if is_line_import(line):
+            if j is None:
+                nu_lines.append(import_tag)
+                j = i
+            cleaned_import_list += clean_imports(line.split(import_tag)[1])
+        else:
+            nu_lines.append(line)
+
+    if j is None:
+        return '\n'.join(nu_lines)
+    cleaned_import_list = sorted(set(cleaned_import_list))
+    nu_lines[j] += ', '.join(cleaned_import_list)
+    return '\n'.join(nu_lines)
+
+# ============================================================
+# Merge repeated 'from pkg import ...' (1-line only)
+# Preserve multi-line grouped imports
+# ============================================================
+def merge_from_import_groups(text=None, file_path=None):
+    if file_path and os.path.isfile(file_path):
+        text = read_from_file(file_path)
+    text = text or ''
+    lines = text.split('\n')
+
+    pkg_to_imports: Dict[str, Set[str]] = {}
+    pkg_to_line_index: Dict[str, int] = {}
+    nu_lines: List[str] = []
+
+    in_group = False
+    for i, line in enumerate(lines):
+        stripped = line.strip()
+
+        # preserve multi-line grouped blocks intact
+        if in_group:
+            nu_lines.append(line)
+            if is_from_group_end(line):
+                in_group = False
+            continue
+
+        if is_from_group_start(line):
+            in_group = True
+            nu_lines.append(line)
+            continue
+
+        if is_line_from_import(line):
+            try:
+                pkg_part, imps_part = line.split(' import ', 1)
+                pkg_name = pkg_part.replace('from ', '').strip()
+                imps = clean_imports(imps_part)
+            except Exception:
+                nu_lines.append(line)
+                continue
+
+            if pkg_name not in pkg_to_imports:
+                pkg_to_imports[pkg_name] = set(imps)
+                pkg_to_line_index[pkg_name] = len(nu_lines)
+                nu_lines.append(line)
+            else:
+                pkg_to_imports[pkg_name].update(imps)
+        else:
+            nu_lines.append(line)
+
+    # Rewrite first occurrences
+    for pkg, idx in pkg_to_line_index.items():
+        all_imps = sorted(pkg_to_imports[pkg])
+        nu_lines[idx] = f"from {pkg} import {', '.join(all_imps)}"
+
+    return '\n'.join(nu_lines)
+
+# ============================================================
+# Pipeline
+# ============================================================
+def clean_imports_pipeline(path: str):
+    raw = read_from_file(path)
+    step1 = combine_lone_imports(text=raw)
+    step2 = merge_from_import_groups(text=step1)
+    return step2
+
+# ============================================================
+# Standalone Run
+# ============================================================
+if __name__ == "__main__":
+    abs_path = "/home/flerb/Documents/pythonTools/modules/src/modules/abstract_utilities/src/abstract_utilities/file_utils/imports/imports.py"
+    cleaned = clean_imports_pipeline(abs_path)
+    print(cleaned)

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/imports/constants.py

@@ -0,0 +1,39 @@
+from .imports import *
+from .module_imports import *
+@dataclass
+class ScanConfig:
+    allowed_exts: Set[str]
+    unallowed_exts: Set[str]
+    exclude_types: Set[str]
+    exclude_dirs: List[str] = field(default_factory=list)
+    exclude_patterns: List[str] = field(default_factory=list)
+DEFAULT_ALLOWED_EXTS: Set[str] = {
+    ".py", ".pyw",                             # python
+    ".js", ".jsx", ".ts", ".tsx", ".mjs",      # JS/TS
+    ".html", ".htm", ".xml",                   # markup
+    ".css", ".scss", ".sass", ".less",         # styles
+    ".json", ".yaml", ".yml", ".toml", ".ini",  # configs
+    ".cfg", ".md", ".markdown", ".rst",        # docs
+    ".sh", ".bash", ".env",                    # scripts/env
+    ".txt"                                     # plain text
+}
+
+DEFAULT_EXCLUDE_TYPES: Set[str] = {
+    "image", "video", "audio", "presentation",
+    "spreadsheet", "archive", "executable"
+}
+
+# never want these—even if they sneak into ALLOWED
+_unallowed = set(get_media_exts(DEFAULT_EXCLUDE_TYPES)) | {'.bak', '.shp', '.cpg', '.dbf', '.shx','.geojson',".pyc",'.shx','.geojson','.prj','.sbn','.sbx'}
+DEFAULT_UNALLOWED_EXTS = {e for e in _unallowed if e not in DEFAULT_ALLOWED_EXTS}
+
+DEFAULT_EXCLUDE_DIRS: Set[str] = {
+    "node_modules", "old","__pycache__", "backups", "backup", "backs", "trash", "depriciated", "old", "__init__"
+}
+
+DEFAULT_EXCLUDE_PATTERNS: Set[str] = {
+    "__init__*", "*.tmp", "*.log", "*.lock", "*.zip","*~"
+}
+REMOTE_RE = re.compile(r"^(?P<host>[^:\s]+@[^:\s]+):(?P<path>/.*)$")
+AllowedPredicate = Optional[Callable[[str], bool]]
+DEFAULT_EXCLUDE_FILE_PATTERNS=DEFAULT_EXCLUDE_PATTERNS

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/imports/imports.py

@@ -0,0 +1,65 @@
+# ============================================================
+# abstract_utilities/imports/imports.py
+# Global imports hub — everything imported here will be
+# automatically available to any module that does:
+#     from ..imports import *
+# ============================================================
+
+
+import os
+import sys, importlib,os
+import sys, importlib, os, inspect
+from pathlib import Path
+import os,sys
+
+
+
+from typing import *
+import re
+
+from typing import *
+from types import MethodType
+import os,re, sys, importlib, inspect, os, importlib.util, hashlib
+import os,tempfile,shutil,logging,ezodf,fnmatch,pytesseract,pdfplumber
+import pandas as pd
+import geopandas as gpd
+from datetime import datetime
+
+from typing import *
+from werkzeug.utils import secure_filename
+from werkzeug.datastructures import FileStorage
+from pdf2image import convert_from_path   # only used for OCR fallback
+# ---- Core standard library modules -------------------------
+import os, sys, re, shlex, glob, platform, textwrap, subprocess, inspect, json, time
+import tempfile, shutil, logging, pathlib, fnmatch, importlib, importlib.util, types
+
+from datetime import datetime
+from types import ModuleType
+
+# ---- Dataclasses and typing --------------------------------
+from dataclasses import dataclass, field
+from typing import (
+    Any, Optional, List, Dict, Set, Tuple,
+    Iterable, Callable, Literal, Union, TypeVar
+)
+
+# ---- Common 3rd-party dependencies --------------------------
+import pandas as pd
+import geopandas as gpd
+import pytesseract
+import pdfplumber
+import PyPDF2
+import ezodf
+from pdf2image import convert_from_path
+from werkzeug.utils import secure_filename
+from werkzeug.datastructures import FileStorage
+
+# ---- Helpers ------------------------------------------------
+import textwrap as tw
+from pprint import pprint
+
+# ============================================================
+# AUTO-EXPORT ALL NON-PRIVATE NAMES
+# ============================================================
+__all__ = [name for name in globals() if not name.startswith("_")]
+

abstract_utilities-0.2.2.490/src/abstract_utilities/file_utils/imports/module_imports.py

@@ -0,0 +1,13 @@
+from .imports import *
+from ...string_clean import eatAll
+from ...list_utils import make_list
+from ...type_utils import get_media_exts, is_media_type, MIME_TYPES, is_str
+from ...ssh_utils import *
+from ...env_utils import *
+from ...read_write_utils import *
+from ...abstract_classes import SingletonMeta
+from ...log_utils import get_logFile
+from ...class_utils import get_caller, get_caller_path, get_caller_dir
+from ...ssh_utils import run_cmd
+
+__all__ = [name for name in globals() if not name.startswith("_")]