csvdoctor 0.1.0__tar.gz

csvdoctor-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 csvdoctor contributors
+
+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.

csvdoctor-0.1.0/PKG-INFO

@@ -0,0 +1,272 @@
+Metadata-Version: 2.4
+Name: csvdoctor
+Version: 0.1.0
+Summary: Diagnose and repair messy CSV files: encodings, delimiters, ragged rows, Excel damage and more. Zero dependencies.
+Author: csvdoctor contributors
+License: MIT
+Project-URL: Homepage, https://github.com/jasonkeanuchristy1-cyber/csvdoctor
+Project-URL: Issues, https://github.com/jasonkeanuchristy1-cyber/csvdoctor/issues
+Project-URL: Changelog, https://github.com/jasonkeanuchristy1-cyber/csvdoctor/blob/main/CHANGELOG.md
+Keywords: csv,data-cleaning,data-quality,encoding,excel,etl,cli,linter
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Information Technology
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Utilities
+Classifier: Topic :: Text Processing :: General
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Dynamic: license-file
+
+# csvdoctor
+
+[![CI](https://github.com/jasonkeanuchristy1-cyber/csvdoctor/actions/workflows/ci.yml/badge.svg)](https://github.com/jasonkeanuchristy1-cyber/csvdoctor/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-blue.svg)
+![Dependencies: none](https://img.shields.io/badge/dependencies-none-brightgreen.svg)
+
+**Find out what is wrong with a CSV file, and fix it, in one command.**
+
+CSV has no standard. Every export is a small gamble: Excel writes `;`-separated
+Windows-1252 in many countries, databases dump UTF-16, web tools add invisible
+byte-order marks, and somebody always sorts the spreadsheet and leaves an empty
+column behind. `csvdoctor` tells you *exactly* what is wrong and writes a clean,
+UTF-8, comma-separated copy, without touching your original.
+
+- **Zero dependencies.** Pure Python standard library. Works anywhere Python 3.9+ does.
+- **Honest.** It re-checks its own output and tells you what it could *not* fix.
+- **Safe by default.** It never silently deletes rows or blanks values. Anything
+  destructive is opt-in.
+- **Usable everywhere.** CLI, Python library, JSON output for scripts, and a
+  [pre-commit](https://pre-commit.com) hook for CI.
+
+## Install
+
+```bash
+pip install git+https://github.com/jasonkeanuchristy1-cyber/csvdoctor.git
+# or, to keep it out of your project environments:
+pipx install git+https://github.com/jasonkeanuchristy1-cyber/csvdoctor.git
+```
+
+## Quick start
+
+```console
+$ csvdoctor check examples/messy.csv
+examples/messy.csv
+  Encoding ........ Windows-1252
+  Delimiter ....... semicolon
+  Line endings .... CRLF
+  Size ............ 9 data rows x 8 columns
+
+  Found 15 issues (3 errors, 10 warnings, 2 info)
+
+  ERROR   RAGGED_ROWS  Wrong number of fields in 1 row (the header has 8): 1 too short.
+            rows: 7
+            -> fixed by `csvdoctor fix`
+
+  ERROR   EXTRA_DATA  Real data beyond the last header column in 1 row. This usually means an
+                      unquoted delimiter inside a value (e.g. a comma in 'Smith, John').
+            rows: 8
+            -> needs manual review
+  ...
+```
+
+(The full report is abridged here; [`examples/messy.csv`](examples/messy.csv) is a
+real, deliberately broken file you can try it on.)
+
+Now fix it:
+
+```console
+$ csvdoctor fix examples/messy.csv --dedupe --normalize-nulls --neutralize-formulas
+Fixed examples/messy.csv -> examples/messy.fixed.csv
+  - Re-encoded from Windows-1252 to UTF-8
+  - Changed delimiter from semicolon to comma
+  - Trimmed whitespace in 2 cells
+  - Repaired garbled text in 1 cell
+  - Removed 1 empty row
+  - Padded 1 short row with empty fields
+  - Dropped 1 empty column: "Notes"
+  - Emptied 1 placeholder value (N/A, #REF!, ...)
+  - Prefixed 1 formula-like cell with an apostrophe
+  - Renamed duplicate columns: "Email" -> "Email_2"
+  - Removed 1 duplicate row
+
+Still needs attention (4):
+(row numbers below refer to the fixed file)
+  ERROR   EXTRA_DATA  ...
+  WARNING EXCEL_SCI_NOTATION  ...
+  WARNING MIXED_TYPES  ...
+  WARNING INCONSISTENT_DATES  ...
+```
+
+The four leftovers are things no tool can safely decide for you: a row with a stray
+delimiter, IDs that Excel already rounded, a `12o` typed instead of `120`, and dates
+that could be day-first *or* month-first. `csvdoctor` shows you where they are and
+leaves the data alone.
+
+## What it checks
+
+| Check | Severity | Resolved by |
+| --- | --- | --- |
+| `EMPTY_FILE` no data at all | error | - |
+| `RAGGED_ROWS` rows with too few fields, or extra *empty* fields | error | `fix` |
+| `EXTRA_DATA` real data past the last column (usually an unquoted delimiter) | error | manual |
+| `DUPLICATE_HEADERS` same column name twice (most tools drop one silently) | error | `fix` renames `x_2` |
+| `ENCODING` not UTF-8 (Windows-1252, Latin-1, UTF-16/32) | warning | `fix` |
+| `LINE_ENDINGS` mixed CRLF / LF / CR (ignores newlines inside quoted cells) | warning | `fix` |
+| `NUL_BYTES` NUL characters in the file | warning | `fix` |
+| `EMPTY_ROWS` blank lines and rows of empty cells | warning | `fix` |
+| `EMPTY_HEADERS` columns without a name | warning | `fix` names `column_N` |
+| `EMPTY_COLUMNS` columns with no data in any row | warning | `fix` |
+| `WHITESPACE` leading/trailing spaces, including non-breaking spaces | warning | `fix` |
+| `INVISIBLE_CHARS` zero-width spaces, word joiners, stray BOMs | warning | `fix` |
+| `MOJIBAKE` text like `Café` from a past UTF-8 / Windows-1252 mix-up | warning | `fix` |
+| `DUPLICATE_ROWS` exact repeated rows | warning | `--dedupe` |
+| `EXCEL_ERRORS` `#REF!`, `#DIV/0!`, `#N/A`... exported as data | warning | `--normalize-nulls` |
+| `FORMULA_INJECTION` cells starting with `=`, `@`, `+cmd`... that spreadsheets may execute | warning | `--neutralize-formulas` |
+| `EXCEL_SCI_NOTATION` IDs/phone numbers Excel rounded to `1.23457E+11` | warning | manual (the digits are gone) |
+| `MIXED_TYPES` a mostly numeric/date column containing text like `12o` | warning | manual |
+| `INCONSISTENT_DATES` several date formats in one column | warning | manual (day/month order is ambiguous) |
+| `BOM` UTF-8 byte-order mark | info | `fix` (`--bom` to keep one for Excel) |
+| `DELIMITER` not a comma | info | `fix` |
+| `NULL_TOKENS` `N/A`, `null`, `none`, `-` standing in for "missing" | info | `--normalize-nulls` |
+
+"`fix`" means the default `csvdoctor fix` handles it. `--flags` are opt-in because they
+change or remove data: for example `NA` is a *real value* in some data sets (Namibia's
+country code), so blanking placeholders is never done unless you ask.
+
+## Command reference
+
+```text
+csvdoctor check FILE [FILE ...]   report problems, change nothing
+csvdoctor fix FILE                write a cleaned copy
+```
+
+Use `-` as the file name to read from standard input.
+
+**`check`**
+
+| Option | Meaning |
+| --- | --- |
+| `--format text\|json` | human report (default) or machine-readable JSON |
+| `--fail-on error\|warning\|info\|never` | exit status 1 if an issue at least this severe exists (default `error`) |
+| `--encoding NAME` | skip detection and read the file as this encoding |
+| `--delimiter CHAR` | skip detection (`,` `;` `tab` `pipe` or any single character) |
+
+**`fix`**
+
+| Option | Meaning |
+| --- | --- |
+| `-o, --output PATH` | where to write (`-` for stdout). Default: `<name>.fixed.csv` next to the input |
+| `--in-place` | overwrite the input; a `.bak` copy of the original is kept |
+| `--dedupe` | remove exact duplicate rows |
+| `--normalize-nulls` | turn `N/A`, `null`, `none`, `-` and spreadsheet errors into empty cells |
+| `--neutralize-formulas` | prefix formula-looking cells with `'` to prevent CSV injection |
+| `--out-delimiter CHAR` | delimiter to write (default `,`) |
+| `--bom` | write a UTF-8 BOM so **Excel** reads accented characters correctly |
+| `--crlf` | write Windows line endings |
+| `--encoding`, `--delimiter` | as for `check` |
+
+Progress messages go to **stderr**, so `csvdoctor fix data.csv -o - | other-tool` is safe.
+
+### Exit codes
+
+| Code | Meaning |
+| --- | --- |
+| `0` | no issues at or above `--fail-on` (`check`), or fixed with no errors remaining (`fix`) |
+| `1` | issues found (`check`), or errors remain after fixing (`fix`) |
+| `2` | usage error or unreadable file |
+
+## Use it in CI and pre-commit
+
+Fail a pull request when a committed CSV is broken:
+
+```yaml
+# .github/workflows/csv.yml
+- run: pip install git+https://github.com/jasonkeanuchristy1-cyber/csvdoctor.git
+- run: csvdoctor check data/*.csv --fail-on error
+```
+
+As a [pre-commit](https://pre-commit.com) hook:
+
+```yaml
+repos:
+  - repo: https://github.com/jasonkeanuchristy1-cyber/csvdoctor
+    rev: v0.1.0
+    hooks:
+      - id: csvdoctor
+```
+
+Machine-readable output for scripts and dashboards:
+
+```bash
+csvdoctor check export.csv --format json | jq '.files[0].summary'
+```
+
+## Use it as a library
+
+```python
+from csvdoctor import read_table, diagnose, repair
+
+raw = open("export.csv", "rb").read()
+
+report = diagnose(read_table(raw))
+for issue in report.issues:
+    print(issue.severity, issue.code, issue.message)
+
+fixed = repair(raw, dedupe=True)      # -> Repaired(data=bytes, actions=[...], ...)
+open("clean.csv", "wb").write(fixed.data)
+print("\n".join(fixed.actions))
+```
+
+| Function | Purpose |
+| --- | --- |
+| `read_table(raw, encoding=None, delimiter=None)` | detect encoding/dialect and parse bytes into a `Table` |
+| `diagnose(table)` | return a `Report` with a list of `Issue` objects (`code`, `severity`, `message`, `rows`, `fix`) |
+| `fix_table(table, ...)` | return cleaned rows plus a log of what changed |
+| `render_csv(rows, delimiter=",", bom=False, crlf=False)` | serialise rows to UTF-8 CSV bytes |
+| `repair(raw, ...)` | all of the above in one call |
+
+## Design principles
+
+1. **Never lose data silently.** Dropping rows and blanking values are opt-in. Rows
+   that cannot be repaired safely are left untouched and reported.
+2. **Don't guess when it matters.** `03/02/2024` could be 3 February or 2 March, so
+   csvdoctor reports mixed date formats instead of "fixing" them.
+3. **Verify, don't claim.** After `fix`, the result is re-parsed and re-checked, and
+   what remains is shown to you.
+4. **Idempotent.** Running `fix` on its own output changes nothing. This is covered by
+   randomised tests.
+
+## Limitations
+
+- The whole file is loaded into memory. Files up to a few hundred MB are fine.
+- Speed is roughly 50,000 rows per second for `check` on a typical 8-column file
+  (pure Python, no dependencies).
+- Encoding and delimiter detection are heuristics. If it guesses wrong, pass
+  `--encoding` / `--delimiter`. Windows-1252 and Latin-1 cannot be told apart with
+  certainty, and csvdoctor assumes Windows-1252 whenever the bytes allow it.
+- It does not validate data against a schema (for that, see
+  [Frictionless](https://frictionlessdata.io/)) and does not infer or convert types.
+
+## Contributing
+
+Bug reports with a small sample file are the most valuable contribution: real-world
+messy CSVs are exactly what makes this tool better. See [CONTRIBUTING.md](CONTRIBUTING.md)
+for setup and how to add a new check.
+
+## License
+
+[MIT](LICENSE)

csvdoctor-0.1.0/README.md

@@ -0,0 +1,240 @@
+# csvdoctor
+
+[![CI](https://github.com/jasonkeanuchristy1-cyber/csvdoctor/actions/workflows/ci.yml/badge.svg)](https://github.com/jasonkeanuchristy1-cyber/csvdoctor/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-blue.svg)
+![Dependencies: none](https://img.shields.io/badge/dependencies-none-brightgreen.svg)
+
+**Find out what is wrong with a CSV file, and fix it, in one command.**
+
+CSV has no standard. Every export is a small gamble: Excel writes `;`-separated
+Windows-1252 in many countries, databases dump UTF-16, web tools add invisible
+byte-order marks, and somebody always sorts the spreadsheet and leaves an empty
+column behind. `csvdoctor` tells you *exactly* what is wrong and writes a clean,
+UTF-8, comma-separated copy, without touching your original.
+
+- **Zero dependencies.** Pure Python standard library. Works anywhere Python 3.9+ does.
+- **Honest.** It re-checks its own output and tells you what it could *not* fix.
+- **Safe by default.** It never silently deletes rows or blanks values. Anything
+  destructive is opt-in.
+- **Usable everywhere.** CLI, Python library, JSON output for scripts, and a
+  [pre-commit](https://pre-commit.com) hook for CI.
+
+## Install
+
+```bash
+pip install git+https://github.com/jasonkeanuchristy1-cyber/csvdoctor.git
+# or, to keep it out of your project environments:
+pipx install git+https://github.com/jasonkeanuchristy1-cyber/csvdoctor.git
+```
+
+## Quick start
+
+```console
+$ csvdoctor check examples/messy.csv
+examples/messy.csv
+  Encoding ........ Windows-1252
+  Delimiter ....... semicolon
+  Line endings .... CRLF
+  Size ............ 9 data rows x 8 columns
+
+  Found 15 issues (3 errors, 10 warnings, 2 info)
+
+  ERROR   RAGGED_ROWS  Wrong number of fields in 1 row (the header has 8): 1 too short.
+            rows: 7
+            -> fixed by `csvdoctor fix`
+
+  ERROR   EXTRA_DATA  Real data beyond the last header column in 1 row. This usually means an
+                      unquoted delimiter inside a value (e.g. a comma in 'Smith, John').
+            rows: 8
+            -> needs manual review
+  ...
+```
+
+(The full report is abridged here; [`examples/messy.csv`](examples/messy.csv) is a
+real, deliberately broken file you can try it on.)
+
+Now fix it:
+
+```console
+$ csvdoctor fix examples/messy.csv --dedupe --normalize-nulls --neutralize-formulas
+Fixed examples/messy.csv -> examples/messy.fixed.csv
+  - Re-encoded from Windows-1252 to UTF-8
+  - Changed delimiter from semicolon to comma
+  - Trimmed whitespace in 2 cells
+  - Repaired garbled text in 1 cell
+  - Removed 1 empty row
+  - Padded 1 short row with empty fields
+  - Dropped 1 empty column: "Notes"
+  - Emptied 1 placeholder value (N/A, #REF!, ...)
+  - Prefixed 1 formula-like cell with an apostrophe
+  - Renamed duplicate columns: "Email" -> "Email_2"
+  - Removed 1 duplicate row
+
+Still needs attention (4):
+(row numbers below refer to the fixed file)
+  ERROR   EXTRA_DATA  ...
+  WARNING EXCEL_SCI_NOTATION  ...
+  WARNING MIXED_TYPES  ...
+  WARNING INCONSISTENT_DATES  ...
+```
+
+The four leftovers are things no tool can safely decide for you: a row with a stray
+delimiter, IDs that Excel already rounded, a `12o` typed instead of `120`, and dates
+that could be day-first *or* month-first. `csvdoctor` shows you where they are and
+leaves the data alone.
+
+## What it checks
+
+| Check | Severity | Resolved by |
+| --- | --- | --- |
+| `EMPTY_FILE` no data at all | error | - |
+| `RAGGED_ROWS` rows with too few fields, or extra *empty* fields | error | `fix` |
+| `EXTRA_DATA` real data past the last column (usually an unquoted delimiter) | error | manual |
+| `DUPLICATE_HEADERS` same column name twice (most tools drop one silently) | error | `fix` renames `x_2` |
+| `ENCODING` not UTF-8 (Windows-1252, Latin-1, UTF-16/32) | warning | `fix` |
+| `LINE_ENDINGS` mixed CRLF / LF / CR (ignores newlines inside quoted cells) | warning | `fix` |
+| `NUL_BYTES` NUL characters in the file | warning | `fix` |
+| `EMPTY_ROWS` blank lines and rows of empty cells | warning | `fix` |
+| `EMPTY_HEADERS` columns without a name | warning | `fix` names `column_N` |
+| `EMPTY_COLUMNS` columns with no data in any row | warning | `fix` |
+| `WHITESPACE` leading/trailing spaces, including non-breaking spaces | warning | `fix` |
+| `INVISIBLE_CHARS` zero-width spaces, word joiners, stray BOMs | warning | `fix` |
+| `MOJIBAKE` text like `Café` from a past UTF-8 / Windows-1252 mix-up | warning | `fix` |
+| `DUPLICATE_ROWS` exact repeated rows | warning | `--dedupe` |
+| `EXCEL_ERRORS` `#REF!`, `#DIV/0!`, `#N/A`... exported as data | warning | `--normalize-nulls` |
+| `FORMULA_INJECTION` cells starting with `=`, `@`, `+cmd`... that spreadsheets may execute | warning | `--neutralize-formulas` |
+| `EXCEL_SCI_NOTATION` IDs/phone numbers Excel rounded to `1.23457E+11` | warning | manual (the digits are gone) |
+| `MIXED_TYPES` a mostly numeric/date column containing text like `12o` | warning | manual |
+| `INCONSISTENT_DATES` several date formats in one column | warning | manual (day/month order is ambiguous) |
+| `BOM` UTF-8 byte-order mark | info | `fix` (`--bom` to keep one for Excel) |
+| `DELIMITER` not a comma | info | `fix` |
+| `NULL_TOKENS` `N/A`, `null`, `none`, `-` standing in for "missing" | info | `--normalize-nulls` |
+
+"`fix`" means the default `csvdoctor fix` handles it. `--flags` are opt-in because they
+change or remove data: for example `NA` is a *real value* in some data sets (Namibia's
+country code), so blanking placeholders is never done unless you ask.
+
+## Command reference
+
+```text
+csvdoctor check FILE [FILE ...]   report problems, change nothing
+csvdoctor fix FILE                write a cleaned copy
+```
+
+Use `-` as the file name to read from standard input.
+
+**`check`**
+
+| Option | Meaning |
+| --- | --- |
+| `--format text\|json` | human report (default) or machine-readable JSON |
+| `--fail-on error\|warning\|info\|never` | exit status 1 if an issue at least this severe exists (default `error`) |
+| `--encoding NAME` | skip detection and read the file as this encoding |
+| `--delimiter CHAR` | skip detection (`,` `;` `tab` `pipe` or any single character) |
+
+**`fix`**
+
+| Option | Meaning |
+| --- | --- |
+| `-o, --output PATH` | where to write (`-` for stdout). Default: `<name>.fixed.csv` next to the input |
+| `--in-place` | overwrite the input; a `.bak` copy of the original is kept |
+| `--dedupe` | remove exact duplicate rows |
+| `--normalize-nulls` | turn `N/A`, `null`, `none`, `-` and spreadsheet errors into empty cells |
+| `--neutralize-formulas` | prefix formula-looking cells with `'` to prevent CSV injection |
+| `--out-delimiter CHAR` | delimiter to write (default `,`) |
+| `--bom` | write a UTF-8 BOM so **Excel** reads accented characters correctly |
+| `--crlf` | write Windows line endings |
+| `--encoding`, `--delimiter` | as for `check` |
+
+Progress messages go to **stderr**, so `csvdoctor fix data.csv -o - | other-tool` is safe.
+
+### Exit codes
+
+| Code | Meaning |
+| --- | --- |
+| `0` | no issues at or above `--fail-on` (`check`), or fixed with no errors remaining (`fix`) |
+| `1` | issues found (`check`), or errors remain after fixing (`fix`) |
+| `2` | usage error or unreadable file |
+
+## Use it in CI and pre-commit
+
+Fail a pull request when a committed CSV is broken:
+
+```yaml
+# .github/workflows/csv.yml
+- run: pip install git+https://github.com/jasonkeanuchristy1-cyber/csvdoctor.git
+- run: csvdoctor check data/*.csv --fail-on error
+```
+
+As a [pre-commit](https://pre-commit.com) hook:
+
+```yaml
+repos:
+  - repo: https://github.com/jasonkeanuchristy1-cyber/csvdoctor
+    rev: v0.1.0
+    hooks:
+      - id: csvdoctor
+```
+
+Machine-readable output for scripts and dashboards:
+
+```bash
+csvdoctor check export.csv --format json | jq '.files[0].summary'
+```
+
+## Use it as a library
+
+```python
+from csvdoctor import read_table, diagnose, repair
+
+raw = open("export.csv", "rb").read()
+
+report = diagnose(read_table(raw))
+for issue in report.issues:
+    print(issue.severity, issue.code, issue.message)
+
+fixed = repair(raw, dedupe=True)      # -> Repaired(data=bytes, actions=[...], ...)
+open("clean.csv", "wb").write(fixed.data)
+print("\n".join(fixed.actions))
+```
+
+| Function | Purpose |
+| --- | --- |
+| `read_table(raw, encoding=None, delimiter=None)` | detect encoding/dialect and parse bytes into a `Table` |
+| `diagnose(table)` | return a `Report` with a list of `Issue` objects (`code`, `severity`, `message`, `rows`, `fix`) |
+| `fix_table(table, ...)` | return cleaned rows plus a log of what changed |
+| `render_csv(rows, delimiter=",", bom=False, crlf=False)` | serialise rows to UTF-8 CSV bytes |
+| `repair(raw, ...)` | all of the above in one call |
+
+## Design principles
+
+1. **Never lose data silently.** Dropping rows and blanking values are opt-in. Rows
+   that cannot be repaired safely are left untouched and reported.
+2. **Don't guess when it matters.** `03/02/2024` could be 3 February or 2 March, so
+   csvdoctor reports mixed date formats instead of "fixing" them.
+3. **Verify, don't claim.** After `fix`, the result is re-parsed and re-checked, and
+   what remains is shown to you.
+4. **Idempotent.** Running `fix` on its own output changes nothing. This is covered by
+   randomised tests.
+
+## Limitations
+
+- The whole file is loaded into memory. Files up to a few hundred MB are fine.
+- Speed is roughly 50,000 rows per second for `check` on a typical 8-column file
+  (pure Python, no dependencies).
+- Encoding and delimiter detection are heuristics. If it guesses wrong, pass
+  `--encoding` / `--delimiter`. Windows-1252 and Latin-1 cannot be told apart with
+  certainty, and csvdoctor assumes Windows-1252 whenever the bytes allow it.
+- It does not validate data against a schema (for that, see
+  [Frictionless](https://frictionlessdata.io/)) and does not infer or convert types.
+
+## Contributing
+
+Bug reports with a small sample file are the most valuable contribution: real-world
+messy CSVs are exactly what makes this tool better. See [CONTRIBUTING.md](CONTRIBUTING.md)
+for setup and how to add a new check.
+
+## License
+
+[MIT](LICENSE)

csvdoctor-0.1.0/pyproject.toml

@@ -0,0 +1,59 @@
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "csvdoctor"
+dynamic = ["version"]
+description = "Diagnose and repair messy CSV files: encodings, delimiters, ragged rows, Excel damage and more. Zero dependencies."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+authors = [{ name = "csvdoctor contributors" }]
+keywords = ["csv", "data-cleaning", "data-quality", "encoding", "excel", "etl", "cli", "linter"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Information Technology",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Utilities",
+    "Topic :: Text Processing :: General",
+    "Typing :: Typed",
+]
+dependencies = []
+
+[project.optional-dependencies]
+dev = ["pytest>=7", "ruff>=0.5", "build", "twine"]
+
+[project.urls]
+Homepage = "https://github.com/jasonkeanuchristy1-cyber/csvdoctor"
+Issues = "https://github.com/jasonkeanuchristy1-cyber/csvdoctor/issues"
+Changelog = "https://github.com/jasonkeanuchristy1-cyber/csvdoctor/blob/main/CHANGELOG.md"
+
+[project.scripts]
+csvdoctor = "csvdoctor.cli:main"
+
+[tool.setuptools.dynamic]
+version = { attr = "csvdoctor.__version__" }
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+csvdoctor = ["py.typed"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py39"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "B"]

csvdoctor-0.1.0/setup.cfg

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

csvdoctor-0.1.0/src/csvdoctor/__init__.py

@@ -0,0 +1,22 @@
+"""csvdoctor: diagnose and repair messy CSV files."""
+
+__version__ = "0.1.0"
+
+from .diagnose import Issue, Report, diagnose  # noqa: E402
+from .fix import FixResult, Repaired, fix_table, render_csv, repair  # noqa: E402
+from .reader import CsvDoctorError, Table, read_table  # noqa: E402
+
+__all__ = [
+    "CsvDoctorError",
+    "FixResult",
+    "Issue",
+    "Repaired",
+    "Report",
+    "Table",
+    "__version__",
+    "diagnose",
+    "fix_table",
+    "read_table",
+    "render_csv",
+    "repair",
+]

csvdoctor-0.1.0/src/csvdoctor/__main__.py

@@ -0,0 +1,4 @@
+from .cli import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())