abstract-utilities 0.2.2.467__py3-none-any.whl → 0.2.2.513__py3-none-any.whl

abstract_utilities/error_utils/imports/__init__.py

@@ -0,0 +1,2 @@
+from .imports import *
+from .module_imports import *

abstract_utilities/error_utils/imports/imports.py

@@ -0,0 +1 @@
+

abstract_utilities/error_utils/imports/module_imports.py

@@ -0,0 +1 @@
+from ...log_utils import get_logger_callable

abstract_utilities/file_utils/__init__.py

@@ -1,3 +1,2 @@
 from .imports import *
-from .file_utils import *
-from .req import call_for_all_tabs,get_for_all_tabs
+from .src import *

abstract_utilities/file_utils/file_utils/imports/__init__.py

@@ -1,5 +1,3 @@
 from .constants import *
-
-from .file_functions import *
 from .imports import *
 from ..imports import *

abstract_utilities/file_utils/file_utils/imports/module_imports.py

@@ -6,7 +6,8 @@ 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
 
 

abstract_utilities/file_utils/file_utils/type_checks.py

@@ -1,34 +1,37 @@
 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, user_at_host: str, timeout: int = 5) -> bool:
+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.
     """
-    cmd = f"[ {test_flag} {shlex.quote(path)} ] && echo 1 || echo 0"
     try:
-        result = subprocess.check_output(
-            ["ssh", user_at_host, cmd],
-            stderr=subprocess.DEVNULL,
-            text=True,
-            timeout=timeout
-        ).strip()
-        return result == "1"
+        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, user_at_host: str) -> bool:
+def is_remote_file(path: str,*args, **kwargs) -> bool:
     """True if remote path is a file."""
-    return _remote_test(path, "-f", user_at_host)
+    return _remote_test(path, "-f", **kwargs)
 
 
-def is_remote_dir(path: str, user_at_host: str) -> bool:
+def is_remote_dir(path: str,*args, **kwargs) -> bool:
     """True if remote path is a directory."""
-    return _remote_test(path, "-d", user_at_host)
+    return _remote_test(path, "-d", **kwargs)
 
 
 def is_local_file(path: str) -> bool:
@@ -42,33 +45,40 @@ def is_local_dir(path: str) -> bool:
 
 
 # --- Unified interface -------------------------------------------------------
-def is_file(path: str,*args, user_at_host: Optional[str] = None,**kwargs) -> bool:
+
+def is_file(path: str,*args,**kwargs) -> bool:
     """Determine if path is a file (works local or remote)."""
-    if user_at_host:
-        return is_remote_file(path, user_at_host)
+    if get_user_pass_host_key(**kwargs):
+        return is_remote_file(path, **kwargs)
     return is_local_file(path)
 
 
-def is_dir(path: str, *args,user_at_host: Optional[str] = None,**kwargs) -> bool:
+def is_dir(path: str, *args,**kwargs) -> bool:
     """Determine if path is a directory (works local or remote)."""
-    if user_at_host:
-        return is_remote_dir(path, user_at_host)
+    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,
-    user_at_host: Optional[str] = None,
+    *args,
+    **kwargs
 ) -> str:
     """
     Return 'file', 'directory', 'missing', or 'unknown'.
     Uses isolated is_file/is_dir functions.
     """
-    if user_at_host:
-        if is_remote_file(path, user_at_host):
+    if get_user_pass_host_key(**kwargs):
+        if is_remote_file(path,**kwargs):
             return "file"
-        elif is_remote_dir(path, user_at_host):
+        elif is_remote_dir(path,**kwargs):
             return "directory"
         else:
             return "missing"

abstract_utilities/file_utils/imports/__init__.py

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

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/file_utils/imports/constants.py

@@ -4,8 +4,11 @@ from .module_imports import *
 class ScanConfig:
     allowed_exts: Set[str]
     unallowed_exts: Set[str]
+    allowed_types: Set[str]
     exclude_types: Set[str]
+    allowed_dirs: List[str] = field(default_factory=list)
     exclude_dirs: List[str] = field(default_factory=list)
+    allowed_patterns: List[str] = field(default_factory=list)
     exclude_patterns: List[str] = field(default_factory=list)
 DEFAULT_ALLOWED_EXTS: Set[str] = {
     ".py", ".pyw",                             # python
@@ -37,3 +40,6 @@ DEFAULT_EXCLUDE_PATTERNS: Set[str] = {
 REMOTE_RE = re.compile(r"^(?P<host>[^:\s]+@[^:\s]+):(?P<path>/.*)$")
 AllowedPredicate = Optional[Callable[[str], bool]]
 DEFAULT_EXCLUDE_FILE_PATTERNS=DEFAULT_EXCLUDE_PATTERNS
+DEFAULT_ALLOWED_PATTENS="*"
+DEFAULT_ALLOWED_DIRS="*"
+DEFAULT_ALLOWED_TYPES="*"

abstract_utilities/file_utils/imports/file_functions.py

@@ -1,5 +1,5 @@
 from .imports import *
-def get_caller_path():
+def get_caller_path(i=None):
     i = i or 1
     frame = inspect.stack()[i]
     return os.path.abspath(frame.filename)

abstract_utilities/file_utils/imports/imports.py

@@ -5,10 +5,26 @@
 #     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 ...imports import *
 from pathlib import Path
+
+
+
+
+from typing import *
+
+from typing import *
+from types import MethodType
+
+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 -------------------------
+
 from datetime import datetime
 from types import ModuleType
 
@@ -20,21 +36,15 @@ from typing import (
 )
 
 # ---- 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/file_utils/imports/module_imports.py

@@ -1,13 +1,8 @@
-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 ...read_write_utils import read_from_file,write_to_file
 from ...log_utils import get_logFile
-from ...class_utils import get_caller, get_caller_path, get_caller_dir
-from ...ssh_utils import run_cmd
+from ...class_utils import get_caller, get_caller_path, get_caller_dir,SingletonMeta,run_pruned_func
 
-__all__ = [name for name in globals() if not name.startswith("_")]

abstract_utilities/file_utils/module_imports.py

@@ -0,0 +1,12 @@
+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
+

abstract_utilities/file_utils/src/__init__.py

@@ -0,0 +1,9 @@
+from .file_filters import *
+from .file_utils import *
+from .filter_params import *
+from .map_utils import *
+from .pdf_utils import *
+from .file_reader import *
+from .find_collect import *
+from .initFunctionsGen import call_for_all_tabs,get_for_all_tabs
+

abstract_utilities/file_utils/src/file_filters.py

@@ -0,0 +1,110 @@
+from ..imports import *
+from .filter_params import *
+from .file_utils import *
+##from abstract_utilities import make_list,get_media_exts, is_media_type
+
+def collect_filepaths(
+    directory: List[str],
+    cfg: ScanConfig=None,
+    allowed_exts: Optional[Set[str]] = False,
+    unallowed_exts: Optional[Set[str]] = False,
+    allowed_types: Optional[Set[str]] = False,
+    exclude_types: Optional[Set[str]] = False,
+    allowed_dirs: Optional[List[str]] = False,
+    exclude_dirs: Optional[List[str]] = False,
+    allowed_patterns: Optional[List[str]] = False,
+    exclude_patterns: Optional[List[str]] = False,
+    add=False,
+    allowed: Optional[Callable[[str], bool]] = None,
+    **kwargs
+    ) -> List[str]:
+    cfg = cfg or define_defaults(
+            allowed_exts = allowed_exts,
+            unallowed_exts = unallowed_exts,
+            allowed_types = allowed_types,
+            exclude_types = exclude_types,
+            allowed_dirs = allowed_dirs,
+            exclude_dirs = exclude_dirs,
+            allowed_patterns = allowed_patterns,
+            exclude_patterns = exclude_patterns,
+            add = add
+        )
+    allowed = allowed or make_allowed_predicate(cfg)
+    directories = make_list(directory)
+    roots = [r for r in directories if r]
+
+    # your existing helpers (get_dirs, get_globs, etc.) stay the same
+    original_dirs = get_allowed_dirs(roots, allowed=allowed)
+    original_globs = get_globs(original_dirs)
+    files = get_allowed_files(original_globs, allowed=allowed)
+
+    for d in get_filtered_dirs(original_dirs, allowed=allowed):
+        files += get_filtered_files(d, allowed=allowed, files=files)
+
+    # de-dupe while preserving order
+    seen, out = set(), []
+    for f in files:
+        if f not in seen:
+            seen.add(f)
+            out.append(f)
+    return out
+
+
+def _fast_walk(
+    root: Path,
+    exts: Iterable[str],
+    skip_dirs: Iterable[str] = (),
+    skip_patterns: Iterable[str] = (),
+) -> List[Path]:
+    exts = tuple(exts)
+    skip_dirs = set(sd.lower() for sd in skip_dirs or ())
+    skip_patterns = tuple(sp.lower() for sp in (skip_patterns or ()))
+
+    out = []
+    for p in root.rglob("*"):
+        # skip directories by name hit
+        if p.is_dir():
+            name = p.name.lower()
+            if name in skip_dirs:
+                # rglob doesn't let us prune mid-iteration cleanly; we just won't collect under it
+                continue
+            # nothing to collect for dirs
+            continue
+
+        # file filters
+        name = p.name.lower()
+        if any(fnmatch.fnmatch(name, pat) for pat in skip_patterns):
+            continue
+        if p.suffix.lower() in exts:
+            out.append(p)
+
+    # de-dup and normalize
+    return sorted({pp.resolve() for pp in out})
+
+
+def enumerate_source_files(
+    src_root: Path,
+    cfg: Optional["ScanConfig"] = None,
+    *,
+    exts: Optional[Iterable[str]] = None,
+    fast_skip_dirs: Optional[Iterable[str]] = None,
+    fast_skip_patterns: Optional[Iterable[str]] = None,
+) -> List[Path]:
+    """
+    Unified enumerator:
+      - If `cfg` is provided: use collect_filepaths(...) with full rules.
+      - Else: fast walk using rglob over `exts` (defaults to EXTS) with optional light excludes.
+    """
+    src_root = Path(src_root)
+
+    if cfg is not None:
+        files = collect_filepaths([str(src_root)], cfg=cfg)
+        return sorted({Path(f).resolve() for f in files})
+
+    # Fast mode
+    return _fast_walk(
+        src_root,
+        exts or EXTS,
+        skip_dirs=fast_skip_dirs or (),
+        skip_patterns=fast_skip_patterns or (),
+    )