minimindslab-csv-sniff 0.1.0__tar.gz

minimindslab_csv_sniff-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 MiniMindsLab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

minimindslab_csv_sniff-0.1.0/PKG-INFO

@@ -0,0 +1,53 @@
+Metadata-Version: 2.4
+Name: minimindslab-csv-sniff
+Version: 0.1.0
+Summary: Infer a CSV dialect from a short text sample and normalize it into a structured, testable description (delimiter, quote character, escape character, line terminator style, and header-likelihood).
+Author: MiniMindsLab
+License: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# MiniMindsLab CSV Sniff
+
+MiniMindsLab CSV Sniff is a tiny, offline helper for inferring CSV dialect details from short text samples.
+
+## Features
+
+- Infers delimiter (comma, tab, semicolon, pipe, or fallback)
+- Reports quote character and escape character assumptions
+- Classifies line terminator style (`lf`, `crlf`, `cr`, or `mixed`)
+- Estimates whether a header row is likely
+- Deterministic output suitable for tests and serialization
+
+## Usage
+
+```python
+from minimindslab_csv_sniff import sniff_csv
+
+sample = "name,age\nAlice,30\nBob,41\n"
+result = sniff_csv(sample)
+print(result)
+# {
+#   'delimiter': ',',
+#   'quotechar': '"',
+#   'escapechar': None,
+#   'lineterminator': 'lf',
+#   'header_likely': True
+# }
+```
+
+## API
+
+### `sniff_csv(sample: str) -> dict`
+
+Raises `ValueError` when input is empty or whitespace-only.
+
+Returns a dictionary with keys:
+
+- `delimiter`
+- `quotechar`
+- `escapechar`
+- `lineterminator`
+- `header_likely`

minimindslab_csv_sniff-0.1.0/README.md

@@ -0,0 +1,42 @@
+# MiniMindsLab CSV Sniff
+
+MiniMindsLab CSV Sniff is a tiny, offline helper for inferring CSV dialect details from short text samples.
+
+## Features
+
+- Infers delimiter (comma, tab, semicolon, pipe, or fallback)
+- Reports quote character and escape character assumptions
+- Classifies line terminator style (`lf`, `crlf`, `cr`, or `mixed`)
+- Estimates whether a header row is likely
+- Deterministic output suitable for tests and serialization
+
+## Usage
+
+```python
+from minimindslab_csv_sniff import sniff_csv
+
+sample = "name,age\nAlice,30\nBob,41\n"
+result = sniff_csv(sample)
+print(result)
+# {
+#   'delimiter': ',',
+#   'quotechar': '"',
+#   'escapechar': None,
+#   'lineterminator': 'lf',
+#   'header_likely': True
+# }
+```
+
+## API
+
+### `sniff_csv(sample: str) -> dict`
+
+Raises `ValueError` when input is empty or whitespace-only.
+
+Returns a dictionary with keys:
+
+- `delimiter`
+- `quotechar`
+- `escapechar`
+- `lineterminator`
+- `header_likely`

minimindslab_csv_sniff-0.1.0/pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["setuptools>=77.0.3"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "minimindslab-csv-sniff"
+version = "0.1.0"
+description = "Infer a CSV dialect from a short text sample and normalize it into a structured, testable description (delimiter, quote character, escape character, line terminator style, and header-likelihood)."
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+authors = [{ name = "MiniMindsLab" }]
+dependencies = []
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]

minimindslab_csv_sniff-0.1.0/setup.cfg

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

minimindslab_csv_sniff-0.1.0/src/minimindslab_csv_sniff/__init__.py

@@ -0,0 +1,103 @@
+"""MiniMindsLab CSV Sniff."""
+
+from __future__ import annotations
+
+import csv
+from io import StringIO
+from typing import Any
+
+__all__ = ["sniff_csv"]
+
+
+def _line_terminator_style(sample: str) -> str:
+    has_crlf = "\r\n" in sample
+    cr_only_count = sample.count("\r") - sample.count("\r\n")
+    has_cr_only = cr_only_count > 0
+    has_lf = sample.count("\n") > sample.count("\r\n") or ("\n" in sample and not has_crlf)
+
+    kinds = sum([1 if has_crlf else 0, 1 if has_cr_only else 0, 1 if has_lf else 0])
+    if kinds > 1:
+        return "mixed"
+    if has_crlf:
+        return "crlf"
+    if has_cr_only:
+        return "cr"
+    return "lf"
+
+
+def _header_likely(lines: list[list[str]]) -> bool:
+    if len(lines) < 2 or not lines[0]:
+        return False
+
+    first = lines[0]
+    rest = lines[1:]
+
+    def is_number(text: str) -> bool:
+        t = text.strip()
+        if not t:
+            return False
+        try:
+            float(t)
+            return True
+        except ValueError:
+            return False
+
+    score = 0
+    for col in range(len(first)):
+        head = first[col].strip()
+        if not head:
+            continue
+        head_is_num = is_number(head)
+
+        numeric_below = 0
+        nonempty_below = 0
+        for row in rest:
+            if col >= len(row):
+                continue
+            v = row[col].strip()
+            if not v:
+                continue
+            nonempty_below += 1
+            if is_number(v):
+                numeric_below += 1
+
+        if nonempty_below == 0:
+            continue
+        if (not head_is_num) and (numeric_below >= max(1, nonempty_below // 2)):
+            score += 1
+
+    return score >= max(1, len(first) // 3)
+
+
+def sniff_csv(sample: str) -> dict[str, Any]:
+    """Infer CSV formatting details from a short sample.
+
+    Returns keys: delimiter, quotechar, escapechar, lineterminator, header_likely.
+    """
+    if not isinstance(sample, str):
+        raise ValueError("sample must be a non-empty string")
+    if sample.strip() == "":
+        raise ValueError("sample must not be empty or whitespace-only")
+
+    sniffer = csv.Sniffer()
+    candidates = [",", "\t", ";", "|", ":"]
+    try:
+        dialect = sniffer.sniff(sample, delimiters="".join(candidates))
+        delimiter = dialect.delimiter
+        quotechar = dialect.quotechar or '"'
+        escapechar = dialect.escapechar
+    except csv.Error:
+        delimiter = ","
+        quotechar = '"'
+        escapechar = None
+
+    reader = csv.reader(StringIO(sample), delimiter=delimiter, quotechar=quotechar)
+    rows = [row for row in reader if row]
+
+    return {
+        "delimiter": delimiter,
+        "quotechar": quotechar,
+        "escapechar": escapechar,
+        "lineterminator": _line_terminator_style(sample),
+        "header_likely": _header_likely(rows),
+    }

minimindslab_csv_sniff-0.1.0/src/minimindslab_csv_sniff.egg-info/PKG-INFO

@@ -0,0 +1,53 @@
+Metadata-Version: 2.4
+Name: minimindslab-csv-sniff
+Version: 0.1.0
+Summary: Infer a CSV dialect from a short text sample and normalize it into a structured, testable description (delimiter, quote character, escape character, line terminator style, and header-likelihood).
+Author: MiniMindsLab
+License: MIT
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# MiniMindsLab CSV Sniff
+
+MiniMindsLab CSV Sniff is a tiny, offline helper for inferring CSV dialect details from short text samples.
+
+## Features
+
+- Infers delimiter (comma, tab, semicolon, pipe, or fallback)
+- Reports quote character and escape character assumptions
+- Classifies line terminator style (`lf`, `crlf`, `cr`, or `mixed`)
+- Estimates whether a header row is likely
+- Deterministic output suitable for tests and serialization
+
+## Usage
+
+```python
+from minimindslab_csv_sniff import sniff_csv
+
+sample = "name,age\nAlice,30\nBob,41\n"
+result = sniff_csv(sample)
+print(result)
+# {
+#   'delimiter': ',',
+#   'quotechar': '"',
+#   'escapechar': None,
+#   'lineterminator': 'lf',
+#   'header_likely': True
+# }
+```
+
+## API
+
+### `sniff_csv(sample: str) -> dict`
+
+Raises `ValueError` when input is empty or whitespace-only.
+
+Returns a dictionary with keys:
+
+- `delimiter`
+- `quotechar`
+- `escapechar`
+- `lineterminator`
+- `header_likely`

minimindslab_csv_sniff-0.1.0/src/minimindslab_csv_sniff.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+LICENSE
+README.md
+pyproject.toml
+src/minimindslab_csv_sniff/__init__.py
+src/minimindslab_csv_sniff.egg-info/PKG-INFO
+src/minimindslab_csv_sniff.egg-info/SOURCES.txt
+src/minimindslab_csv_sniff.egg-info/dependency_links.txt
+src/minimindslab_csv_sniff.egg-info/top_level.txt
+tests/test_csv_sniff.py

minimindslab_csv_sniff-0.1.0/src/minimindslab_csv_sniff.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

minimindslab_csv_sniff-0.1.0/src/minimindslab_csv_sniff.egg-info/top_level.txt

@@ -0,0 +1 @@
+minimindslab_csv_sniff

minimindslab_csv_sniff-0.1.0/tests/test_csv_sniff.py

@@ -0,0 +1,37 @@
+import unittest
+
+from minimindslab_csv_sniff import sniff_csv
+
+
+class TestCsvSniff(unittest.TestCase):
+    def test_comma_with_header(self):
+        sample = "name,age\nAlice,30\nBob,41\n"
+        result = sniff_csv(sample)
+        self.assertEqual(result["delimiter"], ",")
+        self.assertEqual(result["quotechar"], '"')
+        self.assertTrue(result["header_likely"])
+
+    def test_tab_separated(self):
+        sample = "name\tage\nAlice\t30\nBob\t41\n"
+        result = sniff_csv(sample)
+        self.assertEqual(result["delimiter"], "\t")
+
+    def test_empty_or_whitespace_raises(self):
+        with self.assertRaisesRegex(ValueError, "empty or whitespace-only"):
+            sniff_csv("")
+        with self.assertRaisesRegex(ValueError, "empty or whitespace-only"):
+            sniff_csv("   \n\t")
+
+    def test_deterministic_output(self):
+        sample = "city;country\nParis;FR\nRome;IT\n"
+        a = sniff_csv(sample)
+        b = sniff_csv(sample)
+        self.assertEqual(a, b)
+
+    def test_non_string_input_raises(self):
+        with self.assertRaisesRegex(ValueError, "non-empty string"):
+            sniff_csv(None)  # type: ignore[arg-type]
+
+
+if __name__ == "__main__":
+    unittest.main()