abstract-search 0.0.0.1__tar.gz

abstract_search-0.0.0.1/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: abstract_search
+Version: 0.0.0.1
+Summary: Standalone string search across files and directories with allow/exclude filtering; stdlib-only core that reads code, text, pdf, office, and archive-based formats.
+Author-email: putkoff <partners@abstractendeavors.com>
+License: MIT
+Project-URL: Homepage, https://github.com/AbstractEndeavors/abstract_search
+Keywords: search,grep,files,filters,text-extraction,dependency-free
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Software Development :: Libraries
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Provides-Extra: pdf
+Requires-Dist: pdfplumber; extra == "pdf"
+Provides-Extra: ocr
+Requires-Dist: pytesseract; extra == "ocr"
+Requires-Dist: pdf2image; extra == "ocr"
+Provides-Extra: xls
+Requires-Dist: xlrd; extra == "xls"
+Provides-Extra: xlsb
+Requires-Dist: pyxlsb; extra == "xlsb"
+Provides-Extra: dbf
+Requires-Dist: dbfread; extra == "dbf"
+Provides-Extra: parquet
+Requires-Dist: pyarrow; extra == "parquet"
+Provides-Extra: all
+Requires-Dist: pdfplumber; extra == "all"
+Requires-Dist: pytesseract; extra == "all"
+Requires-Dist: pdf2image; extra == "all"
+Requires-Dist: xlrd; extra == "all"
+Requires-Dist: pyxlsb; extra == "all"
+Requires-Dist: dbfread; extra == "all"
+Requires-Dist: pyarrow; extra == "all"
+
+# abstract_search
+
+Standalone string search across files and directories with allow/exclude
+filtering. Stdlib-only at import time — pdf, office, and spreadsheet readers
+load lazily and are optional extras.
+
+```python
+from abstract_search import findContent
+
+# search every readable file under a directory
+hits = findContent("/path/to/project", strings=["needle"], get_lines=True)
+
+# narrow by extension, merge extra excludes with the defaults
+hits = findContent("/path/to/project", strings=["needle"],
+                   allowed_exts="py", exclude_dirs="tests", add=True)
+
+# exact multi-line match locations
+locs = findContent("/path/to/project", strings=["def main(", "return"],
+                   structured=True)
+```
+
+Filter semantics: passing a filter kwarg **replaces** its default set;
+`add=True` **merges** with the defaults instead. Defaults skip
+`node_modules`, `__pycache__`, backups, media/binary extensions, and
+`__init__*` files (see `constants.py`).
+
+```python
+from abstract_search import make_allowed_predicate, filter_allowed_items, search_files
+
+allowed = make_allowed_predicate(exclude_exts=".log", add=True)
+kept = filter_allowed_items(paths, allowed_exts=[".py", ".md"])
+hits = search_files("needle", "/path/to/project")   # line-level SearchHit records
+```
+
+Optional readers: `pip install abstract_search[pdf]` (pdfplumber),
+`[ocr]`, `[xls]`, `[xlsb]`, `[dbf]`, `[parquet]`, or `[all]`.

abstract_search-0.0.0.1/README.md

@@ -0,0 +1,36 @@
+# abstract_search
+
+Standalone string search across files and directories with allow/exclude
+filtering. Stdlib-only at import time — pdf, office, and spreadsheet readers
+load lazily and are optional extras.
+
+```python
+from abstract_search import findContent
+
+# search every readable file under a directory
+hits = findContent("/path/to/project", strings=["needle"], get_lines=True)
+
+# narrow by extension, merge extra excludes with the defaults
+hits = findContent("/path/to/project", strings=["needle"],
+                   allowed_exts="py", exclude_dirs="tests", add=True)
+
+# exact multi-line match locations
+locs = findContent("/path/to/project", strings=["def main(", "return"],
+                   structured=True)
+```
+
+Filter semantics: passing a filter kwarg **replaces** its default set;
+`add=True` **merges** with the defaults instead. Defaults skip
+`node_modules`, `__pycache__`, backups, media/binary extensions, and
+`__init__*` files (see `constants.py`).
+
+```python
+from abstract_search import make_allowed_predicate, filter_allowed_items, search_files
+
+allowed = make_allowed_predicate(exclude_exts=".log", add=True)
+kept = filter_allowed_items(paths, allowed_exts=[".py", ".md"])
+hits = search_files("needle", "/path/to/project")   # line-level SearchHit records
+```
+
+Optional readers: `pip install abstract_search[pdf]` (pdfplumber),
+`[ocr]`, `[xls]`, `[xlsb]`, `[dbf]`, `[parquet]`, or `[all]`.

abstract_search-0.0.0.1/pyproject.toml

@@ -0,0 +1,40 @@
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "abstract_search"
+version = "0.0.0.01"
+description = "Standalone string search across files and directories with allow/exclude filtering; stdlib-only core that reads code, text, pdf, office, and archive-based formats."
+readme = "README.md"
+requires-python = ">=3.8"
+authors = [{ name = "putkoff", email = "partners@abstractendeavors.com" }]
+license = { text = "MIT" }
+keywords = ["search", "grep", "files", "filters", "text-extraction", "dependency-free"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+    "Topic :: Software Development :: Libraries",
+]
+# Intentionally EMPTY — this package's whole reason for existing is to have no deps.
+dependencies = []
+
+# Heavy readers are lazy-loaded per file type; install only what you need.
+[project.optional-dependencies]
+pdf = ["pdfplumber"]
+ocr = ["pytesseract", "pdf2image"]
+xls = ["xlrd"]
+xlsb = ["pyxlsb"]
+dbf = ["dbfread"]
+parquet = ["pyarrow"]
+all = ["pdfplumber", "pytesseract", "pdf2image", "xlrd", "pyxlsb", "dbfread", "pyarrow"]
+
+[project.urls]
+Homepage = "https://github.com/AbstractEndeavors/abstract_search"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+

abstract_search-0.0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

abstract_search-0.0.0.1/src/abstract_search/__init__.py

@@ -0,0 +1,57 @@
+# Standalone string-search + search-filter package. Stdlib-only at import
+# time; heavy readers (pdfplumber, xlrd, ...) load lazily per file type.
+from .constants import (
+    MEDIA_TYPES,
+    get_media_map,
+    get_media_exts,
+    derive_media_type,
+    DEFAULT_ALLOWED_EXTS,
+    DEFAULT_EXCLUDE_EXTS,
+    DEFAULT_EXCLUDE_TYPES,
+    DEFAULT_EXCLUDE_DIRS,
+    DEFAULT_EXCLUDE_PATTERNS,
+    CANONICAL_MAP,
+)
+from .filters import (
+    ScanConfig,
+    make_list,
+    make_allowed_predicate,
+    get_allowed_predicate,
+    filter_allowed_items,
+    define_defaults,
+    ensure_directories,
+    get_file_filters,
+    get_files_and_dirs,
+    get_globs,
+    get_allowed_files,
+    get_allowed_dirs,
+    get_all_allowed_files,
+    get_all_allowed_dirs,
+    get_safe_kwargs,
+    get_safe_canonical_kwargs,
+    get_file_filter_kwargs,
+)
+from .reader import (
+    ExtractedText,
+    SearchHit,
+    WalkConfig,
+    DEFAULT_WALK,
+    extract_text,
+    iter_files,
+    read_paths,
+    search_files,
+    read_any_file,
+    read_file_as_text,
+    read_directory,
+    read_directory_many,
+    read_files,
+)
+from .find_content import (
+    findContent,
+    findContentAndEdit,
+    getPaths,
+    find_lines,
+    stringInContent,
+    request_find_console_stop,
+    reset_find_console_stop,
+)

abstract_search-0.0.0.1/src/abstract_search/constants.py

@@ -0,0 +1,156 @@
+# constants.py — media-type data, default allow/exclude sets, and the
+# canonical-kwargs alias map used to normalize caller keyword arguments.
+import re
+from typing import Callable, List, Optional, Set, Dict
+
+# -------------------------
+# Media types
+# -------------------------
+# Category -> set of extensions.
+MEDIA_TYPES: Dict[str, Set[str]] = {
+    "archive": {".7z", ".bz2", ".dmg", ".egg", ".gz", ".iso", ".jar", ".rar",
+                ".tar", ".tgz", ".war", ".whl", ".xz", ".zip", ".zpaq"},
+    "audio": {".aac", ".aif", ".aiff", ".amr", ".flac", ".m4a", ".mid", ".midi",
+              ".mka", ".mp3", ".ogg", ".opus", ".wav", ".wma"},
+    "code": {".bash", ".c", ".cjs", ".coffee", ".cpp", ".css", ".dockerfile",
+             ".go", ".gql", ".graphql", ".h", ".hpp", ".htm", ".html", ".java",
+             ".js", ".jsx", ".kt", ".less", ".lua", ".makefile", ".mjs", ".php",
+             ".ps1", ".py", ".rb", ".rs", ".sass", ".scss", ".sh", ".sol",
+             ".sql", ".svelte", ".swift", ".ts", ".tsx", ".vue", ".yml"},
+    "data_science": {".avro", ".db", ".h5", ".hdf5", ".ipynb", ".npy", ".npz",
+                     ".parquet", ".pickle", ".sqlite"},
+    "document": {".azw", ".cfg", ".csv", ".doc", ".docx", ".epub", ".ini",
+                 ".json", ".key", ".log", ".markdown", ".md", ".mobi",
+                 ".numbers", ".odt", ".pages", ".pdf", ".rtf", ".tex", ".toml",
+                 ".tsv", ".txt", ".xml", ".yaml", ".yml"},
+    "executable": {".apk", ".app", ".bin", ".deb", ".dll", ".exe", ".ipa", ".rpm"},
+    "font": {".eot", ".otf", ".ttf", ".woff", ".woff2"},
+    "geospatial": {".dbf", ".geojson", ".gpkg", ".gpx", ".kml", ".kmz", ".osm",
+                   ".shp", ".shx", ".tif", ".tiff", ".wkt"},
+    "image": {".ai", ".apng", ".bmp", ".eps", ".gif", ".heic", ".heif", ".ico",
+              ".jp2", ".jpeg", ".jpg", ".jxl", ".png", ".psd", ".raw", ".svg",
+              ".tiff", ".webp"},
+    "pandas_data": {".dta", ".feather", ".h5", ".hdf", ".msgpack", ".orc",
+                    ".parquet", ".pickle", ".pkl", ".sas7bdat", ".sav", ".stata"},
+    "presentation": {".odp", ".ppt", ".pptx"},
+    "spreadsheet": {".csv", ".ods", ".tsv", ".xls", ".xlsx"},
+    "three_d": {".blend", ".fbx", ".glb", ".gltf", ".obj", ".stl", ".usd", ".usdz"},
+    "video": {".3gp", ".asf", ".avi", ".f4v", ".flv", ".m2ts", ".m4v", ".mkv",
+              ".mov", ".mp4", ".mpeg", ".mpg", ".mts", ".ogg", ".vob", ".webm",
+              ".wmv"},
+}
+
+def get_media_map(categories=None):
+    """
+    Return a sub-dict of MEDIA_TYPES for the given categories.
+    If categories is None or empty, return the whole MEDIA_TYPES.
+    """
+    if not categories:
+        return MEDIA_TYPES
+    cats = {str(c) for c in categories}
+    return {c: MEDIA_TYPES[c] for c in cats if c in MEDIA_TYPES}
+
+def get_media_exts(categories=None):
+    """
+    Return a flat, sorted list of all extensions for the given categories.
+    """
+    media_map = get_media_map(categories)
+    return sorted({ext for exts in media_map.values() for ext in exts})
+
+def derive_media_type(obj):
+    ext = None
+    if obj:
+        import os
+        ext = os.path.splitext(str(obj))[-1] or str(obj)
+    if ext:
+        for typ, exts in MEDIA_TYPES.items():
+            if ext in exts:
+                return typ
+
+# -------------------------
+# Default sets
+# -------------------------
+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", ".prj", ".sbn", ".sbx"
+}
+DEFAULT_EXCLUDE_EXTS: Set[str] = {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", "__init__"
+}
+
+DEFAULT_EXCLUDE_PATTERNS: Set[str] = {
+    "__init__*", "*.tmp", "*.log", "*.lock", "*.zip", "*~"
+}
+DEFAULT_EXCLUDE_FILE_PATTERNS = DEFAULT_EXCLUDE_PATTERNS
+DEFAULT_ALLOWED_PATTERNS: List[str] = ["*"]
+DEFAULT_ALLOWED_DIRS: List[str] = ["*"]
+DEFAULT_ALLOWED_TYPES: List[str] = ["*"]
+
+AllowedPredicate = Optional[Callable[[str], bool]]
+
+# -------------------------
+# Canonical kwargs aliases
+# -------------------------
+CANONICAL_MAP = {
+    "directories": ["directory", "directories", "dir", "dirs", "d", "dirname", "paths", "path", "roots", "root"],
+    "files": ["file", "filepath", "file_path", "files", "filepaths", "file_paths", "paths", "path", "f"],
+    "allowed_exts": ["allow_ext", "allowed_ext", "include_ext", "include_exts", "exts_allowed"],
+    "exclude_exts": ["exclude_ext", "excluded_ext", "excluded_exts", "unallowed_ext", "unallowed_exts"],
+    "allowed_types": ["allow_type", "allowed_type", "include_type", "include_types", "types_allowed"],
+    "exclude_types": ["exclude_type", "excluded_type", "excluded_types", "unallowed_type", "unallowed_types"],
+    "allowed_dirs": ["allow_dir", "allowed_dir", "include_dir", "include_dirs", "dirs_allowed"],
+    "exclude_dirs": ["exclude_dir", "excluded_dir", "excluded_dirs", "unallowed_dir", "unallowed_dirs"],
+    "allowed_patterns": ["allow_pattern", "allowed_pattern", "include_pattern", "include_patterns", "patterns_allowed"],
+    "exclude_patterns": ["exclude_pattern", "excluded_pattern", "excluded_patterns", "unallowed_pattern", "unallowed_patterns"],
+    "add": ["add"],
+    "cfg": ["cfg"],
+    "recursive": ["recursive"],
+    "strings": ["strings"],
+    "total_strings": ["total_strings"],
+    "parse_lines": ["parse_lines"],
+    "spec_line": ["spec_line"],
+    "get_lines": ["get_lines"],
+}
+DEFAULT_ALLOWED_EXCLUDE_MAP = {
+    "allowed_exts": {"default": DEFAULT_ALLOWED_EXTS, "type": type(DEFAULT_ALLOWED_EXTS), "canonical": CANONICAL_MAP.get("allowed_exts")},
+    "exclude_exts": {"default": DEFAULT_EXCLUDE_EXTS, "type": type(DEFAULT_EXCLUDE_EXTS), "canonical": CANONICAL_MAP.get("exclude_exts")},
+    "allowed_types": {"default": DEFAULT_ALLOWED_TYPES, "type": type(DEFAULT_ALLOWED_TYPES), "canonical": CANONICAL_MAP.get("allowed_types")},
+    "exclude_types": {"default": DEFAULT_EXCLUDE_TYPES, "type": type(DEFAULT_EXCLUDE_TYPES), "canonical": CANONICAL_MAP.get("exclude_types")},
+    "allowed_dirs": {"default": DEFAULT_ALLOWED_DIRS, "type": type(DEFAULT_ALLOWED_DIRS), "canonical": CANONICAL_MAP.get("allowed_dirs")},
+    "exclude_dirs": {"default": DEFAULT_EXCLUDE_DIRS, "type": type(DEFAULT_EXCLUDE_DIRS), "canonical": CANONICAL_MAP.get("exclude_dirs")},
+    "allowed_patterns": {"default": DEFAULT_ALLOWED_PATTERNS, "type": type(DEFAULT_ALLOWED_PATTERNS), "canonical": CANONICAL_MAP.get("allowed_patterns")},
+    "exclude_patterns": {"default": DEFAULT_EXCLUDE_PATTERNS, "type": type(DEFAULT_EXCLUDE_PATTERNS), "canonical": CANONICAL_MAP.get("exclude_patterns")},
+}
+DEFAULT_CANONICAL_MAP = {
+    "directories": {"default": [], "type": list, "canonical": CANONICAL_MAP.get("directories")},
+    "files": {"default": [], "type": list, "canonical": CANONICAL_MAP.get("files")},
+    **DEFAULT_ALLOWED_EXCLUDE_MAP,
+    "allowed": {"default": None, "type": bool, "canonical": CANONICAL_MAP.get("allowed")},
+    "add": {"default": False, "type": bool, "canonical": CANONICAL_MAP.get("add")},
+    "recursive": {"default": True, "type": bool, "canonical": CANONICAL_MAP.get("recursive")},
+    "strings": {"default": None, "type": list, "canonical": CANONICAL_MAP.get("strings")},
+    "total_strings": {"default": False, "type": bool, "canonical": CANONICAL_MAP.get("total_strings")},
+    "parse_lines": {"default": False, "type": bool, "canonical": CANONICAL_MAP.get("parse_lines")},
+    "spec_line": {"default": False, "type": bool, "canonical": CANONICAL_MAP.get("spec_line")},
+    "get_lines": {"default": False, "type": bool, "canonical": CANONICAL_MAP.get("get_lines")},
+}