dorksmith 0.1.0__tar.gz → 0.2.0__tar.gz

{dorksmith-0.1.0 → dorksmith-0.2.0}/.gitignore

@@ -53,3 +53,6 @@ __pycache__/
 *.pyc
 .pytest_cache/
 .venv/
+
+# Generated engine copy for the SPA (npm run build)
+web/js/engine/

{dorksmith-0.1.0 → dorksmith-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: dorksmith
-Version: 0.1.0
+Version: 0.2.0
 Summary: Deterministic search-dork generator and OSINT/SOCMINT query engine. Catalog-driven, pure Python, no dependencies.
 Project-URL: Homepage, https://github.com/aelena/dorksmith
 Project-URL: Repository, https://github.com/aelena/dorksmith
@@ -78,7 +78,7 @@ validate_query("cache:example.com site:example.com or filetype:.pdf").warnings
 # ["Lower-case 'or' is treated as an ordinary word; ...", "filetype: values take no leading dot ...", "cache: is deprecated: ..."]
 ```
 
-Results are dataclasses; `.to_dict()` gives the same camelCase shape as the HTTP API (`POST /api/v1/dorks/generate`), minus `requestId` and `rateLimit`.
+Results are dataclasses; `.to_dict()` gives the same camelCase shape the npm package and the web app use.
 
 ## API
 
@@ -89,11 +89,11 @@ Results are dataclasses; `.to_dict()` gives the same camelCase shape as the HTTP
 | `expand_handle(username, *, categories=None, platform_ids=None, max_platforms=None, catalogs=None)` | Profile URLs (`status` always `not-checked`) and site-scoped queries. |
 | `infer_input_type(text, known_extensions=None)` | Deterministic input-type suggestion. |
 | `search_url(query, engine="google")` | Search-engine URL, percent-encoded locally. |
-| `validate_catalogs(catalogs)` | Structural/cross-reference validation, same rules as the API's readiness check. |
+| `validate_catalogs(catalogs)` | Structural/cross-reference validation of the catalogs. |
 | `bundled_catalogs()`, `load_catalogs(path)`, `catalog_version()` | Embedded or custom catalogs. |
 | lower-level: `normalize_text`, `try_normalize_domain`, `quote`, `safe_term`, `analyze_query`, `expand_template`, … | Building blocks for custom pipelines. |
 
-`options` keys match the HTTP API: `fileTypes`, `excludeTerms`, `after`, `before`, `site`, `maxVariants`, `organization`, `location`, `role`, `displayName`.
+`options` keys match the npm package: `fileTypes`, `excludeTerms`, `after`, `before`, `site`, `maxVariants`, `organization`, `location`, `role`, `displayName`.
 
 ### Bring your own catalogs
 
@@ -121,7 +121,7 @@ Exit codes: `0` ok, `2` invalid input (or a query with syntax errors for `valida
 ```bash
 python -m pip install -e ".[test]"
 python scripts/sync_catalogs.py      # copies ../../data/*.json into src/dorksmith/data
-python -m pytest -q                  # unit tests + the 151 golden fixtures from the monorepo
+python -m pytest -q                  # unit tests + the 153 golden fixtures from the monorepo
 python -m build                      # sdist + wheel
 ```
 

{dorksmith-0.1.0 → dorksmith-0.2.0}/README.md

@@ -28,7 +28,7 @@ validate_query("cache:example.com site:example.com or filetype:.pdf").warnings
 # ["Lower-case 'or' is treated as an ordinary word; ...", "filetype: values take no leading dot ...", "cache: is deprecated: ..."]
 ```
 
-Results are dataclasses; `.to_dict()` gives the same camelCase shape as the HTTP API (`POST /api/v1/dorks/generate`), minus `requestId` and `rateLimit`.
+Results are dataclasses; `.to_dict()` gives the same camelCase shape the npm package and the web app use.
 
 ## API
 
@@ -39,11 +39,11 @@ Results are dataclasses; `.to_dict()` gives the same camelCase shape as the HTTP
 | `expand_handle(username, *, categories=None, platform_ids=None, max_platforms=None, catalogs=None)` | Profile URLs (`status` always `not-checked`) and site-scoped queries. |
 | `infer_input_type(text, known_extensions=None)` | Deterministic input-type suggestion. |
 | `search_url(query, engine="google")` | Search-engine URL, percent-encoded locally. |
-| `validate_catalogs(catalogs)` | Structural/cross-reference validation, same rules as the API's readiness check. |
+| `validate_catalogs(catalogs)` | Structural/cross-reference validation of the catalogs. |
 | `bundled_catalogs()`, `load_catalogs(path)`, `catalog_version()` | Embedded or custom catalogs. |
 | lower-level: `normalize_text`, `try_normalize_domain`, `quote`, `safe_term`, `analyze_query`, `expand_template`, … | Building blocks for custom pipelines. |
 
-`options` keys match the HTTP API: `fileTypes`, `excludeTerms`, `after`, `before`, `site`, `maxVariants`, `organization`, `location`, `role`, `displayName`.
+`options` keys match the npm package: `fileTypes`, `excludeTerms`, `after`, `before`, `site`, `maxVariants`, `organization`, `location`, `role`, `displayName`.
 
 ### Bring your own catalogs
 
@@ -71,7 +71,7 @@ Exit codes: `0` ok, `2` invalid input (or a query with syntax errors for `valida
 ```bash
 python -m pip install -e ".[test]"
 python scripts/sync_catalogs.py      # copies ../../data/*.json into src/dorksmith/data
-python -m pytest -q                  # unit tests + the 151 golden fixtures from the monorepo
+python -m pytest -q                  # unit tests + the 153 golden fixtures from the monorepo
 python -m build                      # sdist + wheel
 ```
 

{dorksmith-0.1.0 → dorksmith-0.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dorksmith"
-version = "0.1.0"
+version = "0.2.0"
 description = "Deterministic search-dork generator and OSINT/SOCMINT query engine. Catalog-driven, pure Python, no dependencies."
 readme = "README.md"
 license = { file = "LICENSE" }

{dorksmith-0.1.0 → dorksmith-0.2.0}/src/dorksmith/__init__.py

@@ -29,7 +29,7 @@ from .placeholders import ALL_PLACEHOLDERS, OPTIONAL_BY_DEFAULT, placeholders_in
 from .quoting import exclusion, looks_like_syntax, operator_value, or_group, quote, safe_term, safe_terms, unquote
 from .validator import validate_catalogs
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"
 
 
 def catalog_version(catalogs: Catalogs | None = None) -> str:

{dorksmith-0.1.0 → dorksmith-0.2.0}/src/dorksmith/normalizer.py

@@ -51,12 +51,34 @@ def normalize_text(value: str | None) -> str:
 
 
 def words(normalized: str) -> tuple[list[str], bool]:
-    """Split normalised text into words, unwrapping a fully quoted phrase ("a b" -> a b)."""
+    """Split normalised text into terms.
+
+    A fully quoted input ("a b") is unwrapped; quoted phrases inside the text (alice "antonio elena")
+    are kept as single terms, quotes included, so templates preserve them.
+    """
     s = normalized
     quoted = len(s) >= 2 and s[0] == '"' and s[-1] == '"' and s.find('"', 1) == len(s) - 1
     if quoted:
         s = s[1:-1].strip()
-    return [w for w in (p.strip() for p in s.split(" ")) if w], quoted
+    out: list[str] = []
+    i, n = 0, len(s)
+    while i < n:
+        if s[i] == " ":
+            i += 1
+            continue
+        if s[i] == '"':
+            end = s.find('"', i + 1)
+            inner = (s[i + 1:] if end < 0 else s[i + 1:end]).strip()
+            if inner:
+                out.append(f'"{inner}"')
+            i = n if end < 0 else end + 1
+            continue
+        j = i
+        while j < n and s[j] != " ":
+            j += 1
+        out.append(s[i:j])
+        i = j
+    return out, quoted
 
 
 def try_normalize_domain(value: str | None) -> str | None:

{dorksmith-0.1.0 → dorksmith-0.2.0}/src/dorksmith/quoting.py

@@ -27,6 +27,8 @@ def looks_like_syntax(s: str) -> bool:
         return True
     if s[0] in "-+~()|":
         return True
+    if len(s) > 1 and s[0] in "@#":  # social-handle / hashtag operators
+        return True
     if s[-1] in "()":
         return True
     colon = s.find(":")
@@ -36,8 +38,12 @@ def looks_like_syntax(s: str) -> bool:
 
 
 def safe_term(word: str | None) -> str:
-    """A single word emitted unquoted; words that would parse as syntax are quoted so they stay literal."""
-    s = (word or "").strip().replace('"', "")
+    """A single term emitted unquoted; terms that would parse as syntax are quoted so they stay literal,
+    and a term the user already quoted ("antonio elena") is kept as a quoted phrase."""
+    raw = (word or "").strip()
+    if len(raw) >= 2 and raw[0] == '"' and raw[-1] == '"':
+        return quote(raw)
+    s = raw.replace('"', "")
     if not s:
         return ""
     if looks_like_syntax(s):

{dorksmith-0.1.0 → dorksmith-0.2.0}/tests/test_golden.py

@@ -11,7 +11,7 @@ import pytest
 
 from dorksmith import bundled_catalogs, generate, validate_catalogs
 
-FIXTURES = Path(__file__).resolve().parents[3] / "tests" / "Dorksmith.Api.Tests" / "Golden" / "fixtures"
+FIXTURES = Path(__file__).resolve().parents[3] / "tests" / "golden"
 FILES = sorted(FIXTURES.glob("*.json")) if FIXTURES.is_dir() else []
 _covered: set[str] = set()
 

dorksmith-0.2.0/tests/test_phrases.py

@@ -0,0 +1,42 @@
+"""Quoted phrases and social-style tokens inside free-text input."""
+from __future__ import annotations
+
+from dorksmith import analyze_query, bundled_catalogs, generate, safe_term
+from dorksmith.normalizer import words
+
+
+def test_words_keeps_user_quoted_phrases() -> None:
+    assert words('aelena "antonio elena"')[0] == ["aelena", '"antonio elena"']
+    assert words('"antonio elena" aelena x')[0] == ['"antonio elena"', "aelena", "x"]
+    assert words('a "" b')[0] == ["a", "b"]
+    assert words('a "unterminated phrase')[0] == ["a", '"unterminated phrase"']
+    assert words('"whole input quoted"') == (["whole", "input", "quoted"], True)
+
+
+def test_safe_term_keeps_phrases_and_neutralises_social_tokens() -> None:
+    assert safe_term('"antonio elena"') == '"antonio elena"'
+    assert safe_term('"nested "quotes" inside"') == '"nested quotes inside"'
+    assert safe_term('""') == ""
+    assert safe_term("@aelena") == '"@aelena"'
+    assert safe_term("#osint") == '"#osint"'
+    assert safe_term("@") == "@"
+    assert safe_term("a@b") == "a@b"
+
+
+def test_quoted_phrase_survives_variants() -> None:
+    r = generate('aelena "antonio elena"', "keyword", "general-discovery", options={"maxVariants": 12})
+    queries = [v.query for v in r.variants]
+    assert 'aelena "antonio elena"' in queries
+    assert '(aelena OR "antonio elena")' in queries
+    assert '"aelena antonio elena"' in queries
+    assert all('""' not in q for q in queries)
+
+
+def test_leading_at_is_quoted_without_operator_warning() -> None:
+    r = generate("@aelena antonio elena", "keyword", "general-discovery", options={"maxVariants": 12})
+    for v in r.variants:
+        assert "@" not in v.operators, v.query
+        assert v.warnings == [], v.query
+    assert any(v.query == '"@aelena" antonio elena' for v in r.variants)
+    catalogs = bundled_catalogs()
+    assert analyze_query('"@aelena" antonio elena', catalogs.operators["google"], catalogs.operator_index("google")).operators == ['"']