datamarket 0.9.25__tar.gz → 0.9.27__tar.gz

{datamarket-0.9.25 → datamarket-0.9.27}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: datamarket
-Version: 0.9.25
+Version: 0.9.27
 Summary: Utilities that integrate advanced scraping knowledge into just one library.
 License: GPL-3.0-or-later
 Author: DataMarket
@@ -59,7 +59,6 @@ Provides-Extra: soda-core-postgres
 Provides-Extra: stem
 Provides-Extra: tqdm
 Provides-Extra: undetected-chromedriver
-Provides-Extra: unidecode
 Provides-Extra: xmltodict
 Requires-Dist: SQLAlchemy (>=2.0.0,<3.0.0) ; extra == "alchemy"
 Requires-Dist: azure-storage-blob (>=12.0.0,<13.0.0) ; extra == "azure-storage-blob"
@@ -84,10 +83,12 @@ Requires-Dist: google-auth-httplib2 (>=0.2.0,<0.3.0) ; extra == "google-auth-htt
 Requires-Dist: google-auth-oauthlib (>=1.0.0,<2.0.0) ; extra == "google-auth-oauthlib"
 Requires-Dist: html2text (>=2024.0.0,<2025.0.0) ; extra == "html2text"
 Requires-Dist: httpx[http2] (>=0.28.0,<0.29.0) ; extra == "httpx"
+Requires-Dist: inflection (>=0.5.0,<0.6.0)
 Requires-Dist: jinja2 (>=3.0.0,<4.0.0)
 Requires-Dist: json5 (>=0.10.0,<0.11.0) ; extra == "json5"
 Requires-Dist: lxml[html-clean] (>=5.0.0,<6.0.0) ; extra == "lxml"
 Requires-Dist: nodriver (>=0.44,<0.45) ; extra == "nodriver"
+Requires-Dist: numpy (>=2.0.0,<3.0.0)
 Requires-Dist: openpyxl (>=3.0.0,<4.0.0) ; extra == "openpyxl"
 Requires-Dist: pandas (>=2.0.0,<3.0.0) ; extra == "pandas"
 Requires-Dist: pandera (>=0.22.0,<0.23.0) ; extra == "pandera"
@@ -102,6 +103,7 @@ Requires-Dist: pymupdf (>=1.0.0,<2.0.0) ; extra == "pymupdf"
 Requires-Dist: pysocks (>=1.0.0,<2.0.0) ; extra == "pysocks"
 Requires-Dist: pyspark (>=3.0.0,<4.0.0) ; extra == "pyspark"
 Requires-Dist: pytest (>=8.0.0,<9.0.0) ; extra == "pytest"
+Requires-Dist: python-string-utils (>=1.0.0,<2.0.0)
 Requires-Dist: rapidfuzz (>=3.0.0,<4.0.0) ; extra == "rapidfuzz"
 Requires-Dist: requests (>=2.0.0,<3.0.0)
 Requires-Dist: retry (>=0.9.0,<0.10.0) ; extra == "retry"
@@ -112,7 +114,7 @@ Requires-Dist: stem (>=1.0.0,<2.0.0) ; extra == "stem" or extra == "proxy"
 Requires-Dist: tenacity (>=9.0.0,<10.0.0)
 Requires-Dist: tqdm (>=4.0.0,<5.0.0) ; extra == "tqdm"
 Requires-Dist: typer (>=0.15.0,<0.16.0)
-Requires-Dist: unidecode (>=1.0.0,<2.0.0) ; extra == "unidecode"
+Requires-Dist: unidecode (>=1.0.0,<2.0.0)
 Requires-Dist: xmltodict (>=0.14.0,<0.15.0) ; extra == "xmltodict"
 Project-URL: Documentation, https://github.com/Data-Market/datamarket
 Project-URL: Homepage, https://datamarket.es

{datamarket-0.9.25 → datamarket-0.9.27}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "datamarket"
-version = "0.9.25"
+version = "0.9.27"
 description = "Utilities that integrate advanced scraping knowledge into just one library."
 authors = ["DataMarket <techsupport@datamarket.es>"]
 license = "GPL-3.0-or-later"
@@ -26,9 +26,12 @@ pendulum = "^3.0.0"
 croniter = "^3.0.0"
 dynaconf = "^3.0.0"
 jinja2 = "^3.0.0"
+inflection = "~0.5.0"
+python-string-utils = "^1.0.0"
+unidecode = "^1.0.0"
+numpy = "^2.0.0"
 
 boto3 = { version = "~1.35.0", optional = true }
-unidecode = { version = "^1.0.0", optional = true }
 lxml = { extras = ["html-clean"], version = "^5.0.0", optional = true }
 tqdm = { version = "^4.0.0", optional = true }
 pandas = { version = "^2.0.0", optional = true }
@@ -74,7 +77,6 @@ camoufox = { extras = ["geoip"], version = "~0.4.11", optional = true }
 
 [tool.poetry.extras]
 boto3 = ["boto3"]
-unidecode = ["unidecode"]
 lxml = ["lxml"]
 tqdm = ["tqdm"]
 pandas = ["pandas"]

datamarket-0.9.27/src/datamarket/utils/strings.py

@@ -0,0 +1,152 @@
+########################################################################################################################
+# IMPORTS
+
+from enum import Enum, auto
+from typing import Any
+import unicodedata
+
+import numpy as np
+from unidecode import unidecode
+from inflection import parameterize, underscore, titleize, camelize
+from string_utils import prettify, strip_html
+
+########################################################################################################################
+# CLASSES
+
+
+class NormalizationMode(Enum):
+    NONE = auto()
+    BASIC = auto()  # removes accents and converts punctuation to spaces
+    SYMBOLS = auto()  # translates only symbols to Unicode name
+    FULL = auto()  # BASIC + SYMBOLS
+
+
+class NamingConvention(Enum):
+    NONE = auto()  # no style change
+    CONSTANT = auto()  # CONSTANT_CASE (uppercase, underscores)
+    SNAKE = auto()  # snake_case (lowercase, underscores)
+    CAMEL = auto()  # camelCase (capitalize words except first one, no spaces)
+    PASCAL = auto()  # PascalCase (capitalize words including first one, no spaces)
+    PARAM = auto()  # parameterize (hyphens)
+    TITLE = auto()  # titleize (capitalize words)
+
+
+########################################################################################################################
+# FUNCTIONS
+
+
+def transliterate_symbols(s: str) -> str:
+    """
+    Translates Unicode symbols (category S*) in the input string to their lowercase Unicode names,
+    with spaces replaced by underscores. Other characters remain unchanged.
+
+    Args:
+        s: The input string.
+
+    Returns:
+        The string with symbols transliterated.
+    """
+    out: list[str] = []
+    for c in s:
+        if unicodedata.category(c).startswith("S"):
+            name = unicodedata.name(c, "")
+            if name:
+                out.append(name.lower().replace(" ", "_"))
+        else:
+            out.append(c)
+    return "".join(out)
+
+
+def normalize(
+    s: Any, mode: NormalizationMode = NormalizationMode.BASIC, naming: NamingConvention = NamingConvention.NONE
+) -> str:
+    """
+    Normalizes and applies a naming convention to the input.
+
+    Handles None and NaN values by returning an empty string. Converts non-string inputs to strings.
+
+    Normalization is applied according to `mode`:
+    - NONE: Returns the input as a string without any normalization.
+    - BASIC: Removes accents, converts punctuation and spaces to single spaces, and preserves alphanumeric characters.
+    - SYMBOLS: Translates only Unicode symbols (category S*) to their lowercase Unicode names with underscores.
+    - FULL: Applies both BASIC and SYMBOLS normalization.
+
+    After normalization, a naming convention is applied according to `naming`:
+    - NONE: Returns the normalized text.
+    - CONSTANT: Converts to CONSTANT_CASE (uppercase with underscores).
+    - SNAKE: Converts to snake_case (lowercase with underscores).
+    - CAMEL: Converts to camelCase (lowercase first word, capitalize subsequent words, no spaces).
+    - PASCAL: Converts to PascalCase (capitalize all words, no spaces).
+    - PARAM: Converts to parameterize (lowercase with hyphens).
+    - TITLE: Converts to Title Case (capitalize each word).
+
+    Args:
+        s: The input value to normalize and format. Can be any type.
+        mode: The normalization mode to apply. Defaults to NormalizationMode.BASIC.
+        naming: The naming convention to apply. Defaults to NamingConvention.NONE.
+
+    Returns:
+        The normalized and formatted string.
+    """
+    # Parameter mapping
+    if isinstance(mode, str):
+        mode = NormalizationMode[mode]
+    if isinstance(naming, str):
+        naming = NamingConvention[naming]
+
+    # Handling null values
+    if s is None or (isinstance(s, float) and np.isnan(s)):
+        normalized = ""
+    elif not isinstance(s, str):
+        return str(s)
+    else:
+        text = prettify(strip_html(str(s), True))
+        if mode is NormalizationMode.NONE:
+            normalized = text
+        elif mode is NormalizationMode.SYMBOLS:
+            normalized = transliterate_symbols(text)
+        else:
+            # BASIC and FULL: remove accents and lowercase
+            normalized = unidecode(text).lower()
+            tokens: list[str] = []
+            current: list[str] = []
+
+            def flush_current():
+                nonlocal current
+                if current:
+                    tokens.append("".join(current))
+                    current.clear()
+
+            for c in normalized:
+                cat = unicodedata.category(c)
+                if c.isalnum():
+                    current.append(c)
+                elif mode is NormalizationMode.FULL and cat.startswith("S"):
+                    flush_current()
+                    name = unicodedata.name(c, "")
+                    if name:
+                        tokens.append(name.lower().replace(" ", "_"))
+                elif cat.startswith("P") or c.isspace():
+                    flush_current()
+                # other characters ignored
+
+            flush_current()
+            normalized = " ".join(tokens)
+
+    # Apply naming convention
+    if naming is NamingConvention.NONE:
+        return normalized
+    if naming is NamingConvention.PARAM:
+        return parameterize(normalized)
+    if naming is NamingConvention.TITLE:
+        return titleize(normalized)
+
+    underscored = underscore(parameterize(normalized))
+    if naming is NamingConvention.CONSTANT:
+        return underscored.upper()
+    if naming is NamingConvention.CAMEL:
+        return camelize(underscored, False)
+    if naming is NamingConvention.PASCAL:
+        return camelize(underscored)
+
+    return underscored