Jef Roosens
d6689a6c83
- Add extract_table_blocks() to split a document into contiguous table blocks, ignoring prose, headings, and blank lines between them - Add parse_document() as the new top-level entry point that runs extract_table_blocks + detect_has_duration_column + parse_table per block and returns a combined flat list of rows - Guard against empty End cells (e.g. in-progress rows) by validating the end field before calculating duration - Update cli.py to use parse_document() instead of the manual detect + parse combo - Add tests for extract_table_blocks and parse_document, including two smoke tests against the real 2026-W21 weekly timesheet file
264 lines
9.3 KiB
Python
264 lines
9.3 KiB
Python
import os
|
||
|
||
import pytest
|
||
|
||
from timesheets.parser import (
|
||
aggregate_rows,
|
||
build_description,
|
||
detect_has_duration_column,
|
||
extract_table_blocks,
|
||
parse_document,
|
||
parse_table,
|
||
)
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Fixtures / shared data
|
||
# ---------------------------------------------------------------------------
|
||
|
||
WITH_DURATION = [
|
||
"| Start | End | Duration | Project | Story | Note |",
|
||
"|-------|-------|----------|---------|-------------|---------|",
|
||
"| 08:00 | 08:30 | 00:30 | bugs | story one | |",
|
||
"| 08:30 | 09:00 | 00:30 | bugs | story one | |",
|
||
"| 09:00 | 09:15 | 00:15 | scrum | | dsu |",
|
||
]
|
||
|
||
WITHOUT_DURATION = [
|
||
"| Start | End | Project | Story | Note |",
|
||
"|-------|-------|---------|-------------|---------|",
|
||
"| 08:00 | 08:30 | bugs | story one | |",
|
||
"| 08:30 | 09:15 | scrum | | dsu |",
|
||
]
|
||
|
||
WEEK_FILE = os.path.join(os.path.dirname(__file__), "2026 - W21.md")
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# detect_has_duration_column
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestDetectHasDurationColumn:
|
||
def test_with_duration(self):
|
||
assert detect_has_duration_column(WITH_DURATION) is True
|
||
|
||
def test_without_duration(self):
|
||
assert detect_has_duration_column(WITHOUT_DURATION) is False
|
||
|
||
def test_no_header_defaults_to_true(self):
|
||
assert detect_has_duration_column(["no table here"]) is True
|
||
|
||
def test_case_insensitive(self):
|
||
lines = ["| Start | End | DURATION | Project | Story | Note |"]
|
||
assert detect_has_duration_column(lines) is True
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# extract_table_blocks
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestExtractTableBlocks:
|
||
def test_single_table(self):
|
||
blocks = extract_table_blocks(WITH_DURATION)
|
||
assert len(blocks) == 1
|
||
assert blocks[0] == WITH_DURATION
|
||
|
||
def test_two_tables_separated_by_prose(self):
|
||
lines = WITH_DURATION + ["", "# Next day", "some prose", ""] + WITHOUT_DURATION
|
||
blocks = extract_table_blocks(lines)
|
||
assert len(blocks) == 2
|
||
|
||
def test_prose_between_tables_not_included(self):
|
||
lines = WITH_DURATION + ["some note"] + WITHOUT_DURATION
|
||
blocks = extract_table_blocks(lines)
|
||
assert len(blocks) == 2
|
||
assert all("some note" not in b for b in blocks)
|
||
|
||
def test_single_line_table_discarded(self):
|
||
lines = ["| Start | End |"]
|
||
assert extract_table_blocks(lines) == []
|
||
|
||
def test_empty_input(self):
|
||
assert extract_table_blocks([]) == []
|
||
|
||
def test_no_tables(self):
|
||
assert extract_table_blocks(["# heading", "", "prose"]) == []
|
||
|
||
def test_table_at_end_of_file_captured(self):
|
||
lines = ["# heading", ""] + WITH_DURATION # no trailing newline
|
||
blocks = extract_table_blocks(lines)
|
||
assert len(blocks) == 1
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# parse_table
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestParseTable:
|
||
def test_with_duration_column(self):
|
||
rows = parse_table(WITH_DURATION, has_duration_col=True)
|
||
assert len(rows) == 3
|
||
assert rows[0]["project"] == "bugs"
|
||
assert rows[0]["duration_hours"] == 0.5
|
||
assert rows[2]["project"] == "scrum"
|
||
assert rows[2]["note"] == "dsu"
|
||
|
||
def test_without_duration_column(self):
|
||
rows = parse_table(WITHOUT_DURATION, has_duration_col=False)
|
||
assert len(rows) == 2
|
||
assert rows[0]["duration_hours"] == 0.5 # 08:00–08:30
|
||
assert rows[1]["duration_hours"] == 0.75 # 08:30–09:15
|
||
|
||
def test_header_row_skipped(self):
|
||
rows = parse_table(WITH_DURATION)
|
||
assert all(r["start"] != "Start" for r in rows)
|
||
|
||
def test_separator_row_skipped(self):
|
||
rows = parse_table(WITH_DURATION)
|
||
assert all(r["start"] != "---" for r in rows)
|
||
|
||
def test_markdown_link_stripped_in_story(self):
|
||
lines = [
|
||
"| Start | End | Duration | Project | Story | Note |",
|
||
"|-------|-------|----------|---------|----------------------------|------|",
|
||
"| 08:00 | 08:30 | 00:30 | bugs | [ticket 1](:/abc123) | |",
|
||
]
|
||
rows = parse_table(lines)
|
||
assert rows[0]["story"] == "ticket 1"
|
||
|
||
def test_invalid_duration_row_skipped(self):
|
||
lines = [
|
||
"| Start | End | Duration | Project | Story | Note |",
|
||
"|-------|-------|----------|---------|-------|------|",
|
||
"| 08:00 | 08:30 | bad | bugs | | |",
|
||
]
|
||
assert parse_table(lines) == []
|
||
|
||
def test_empty_end_time_row_skipped(self):
|
||
lines = [
|
||
"| Start | End | Project | Story | Note |",
|
||
"|-------|-------|---------|-------|------|",
|
||
"| 09:55 | | bugs | | |",
|
||
]
|
||
assert parse_table(lines, has_duration_col=False) == []
|
||
|
||
def test_empty_input(self):
|
||
assert parse_table([]) == []
|
||
|
||
def test_non_table_lines_ignored(self):
|
||
lines = ["# My Timesheet", "", "Some prose."] + WITH_DURATION
|
||
rows = parse_table(lines)
|
||
assert len(rows) == 3
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# parse_document
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestParseDocument:
|
||
def test_single_table(self):
|
||
rows = parse_document(WITHOUT_DURATION)
|
||
assert len(rows) == 2
|
||
|
||
def test_multiple_tables_combined(self):
|
||
lines = WITHOUT_DURATION + ["", "# Next day", ""] + WITHOUT_DURATION
|
||
rows = parse_document(lines)
|
||
assert len(rows) == 4
|
||
|
||
def test_prose_between_tables_ignored(self):
|
||
lines = (
|
||
WITHOUT_DURATION + ["some notes", "- a bullet point", ""] + WITHOUT_DURATION
|
||
)
|
||
rows = parse_document(lines)
|
||
assert len(rows) == 4
|
||
|
||
def test_mixed_duration_formats(self):
|
||
lines = WITH_DURATION + ["", "## Next day", ""] + WITHOUT_DURATION
|
||
rows = parse_document(lines)
|
||
assert len(rows) == 5 # 3 from WITH_DURATION + 2 from WITHOUT_DURATION
|
||
|
||
def test_empty_input(self):
|
||
assert parse_document([]) == []
|
||
|
||
def test_week_file(self):
|
||
"""Smoke test against the real W21 weekly timesheet file."""
|
||
with open(WEEK_FILE, encoding="utf-8") as f:
|
||
lines = f.read().splitlines()
|
||
rows = parse_document(lines)
|
||
# File has 5 daily tables; expect a healthy number of rows
|
||
assert len(rows) > 20
|
||
# All rows must have expected keys
|
||
for row in rows:
|
||
assert "project" in row
|
||
assert "duration_hours" in row
|
||
assert row["duration_hours"] > 0
|
||
# The incomplete row (09:55 | empty end) must have been skipped
|
||
incomplete = [
|
||
r for r in rows if r["start"] == "09:55" and r["project"] == "bugs"
|
||
]
|
||
assert all(r["duration_hours"] > 0 for r in incomplete)
|
||
|
||
def test_week_file_no_markdown_links_in_stories(self):
|
||
"""Markdown link syntax must be stripped from story/note fields."""
|
||
with open(WEEK_FILE, encoding="utf-8") as f:
|
||
lines = f.read().splitlines()
|
||
rows = parse_document(lines)
|
||
for row in rows:
|
||
assert "](:" not in row["story"], (
|
||
f"Link not stripped in story: {row['story']!r}"
|
||
)
|
||
assert "](:" not in row["note"], (
|
||
f"Link not stripped in note: {row['note']!r}"
|
||
)
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# build_description
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestBuildDescription:
|
||
def test_story_and_note(self):
|
||
assert build_description("story", "note") == "story - note"
|
||
|
||
def test_story_only(self):
|
||
assert build_description("story", "") == "story"
|
||
|
||
def test_note_only(self):
|
||
assert build_description("", "note") == "note"
|
||
|
||
def test_both_empty(self):
|
||
assert build_description("", "") == "/"
|
||
|
||
def test_strips_whitespace(self):
|
||
assert build_description(" story ", " note ") == "story - note"
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# aggregate_rows
|
||
# ---------------------------------------------------------------------------
|
||
|
||
|
||
class TestAggregateRows:
|
||
def test_same_project_story_summed(self):
|
||
rows = parse_table(WITH_DURATION)
|
||
aggregated = aggregate_rows(rows)
|
||
bugs = next(e for e in aggregated if e["project"] == "bugs")
|
||
assert bugs["quantity"] == 1.0 # 00:30 + 00:30
|
||
|
||
def test_distinct_entries_preserved(self):
|
||
rows = parse_table(WITH_DURATION)
|
||
aggregated = aggregate_rows(rows)
|
||
assert len(aggregated) == 2 # bugs/story-one and scrum/dsu
|
||
|
||
def test_insertion_order_preserved(self):
|
||
rows = parse_table(WITH_DURATION)
|
||
aggregated = aggregate_rows(rows)
|
||
assert aggregated[0]["project"] == "bugs"
|
||
assert aggregated[1]["project"] == "scrum"
|
||
|
||
def test_empty_input(self):
|
||
assert aggregate_rows([]) == []
|