"""T-CLK-* — the legacy clockify.test.ts fixture suite, ported 1:1 (06-test-plan §2.1). Fixture values are VERBATIM from /srv/apps/work/tests/clockify.test.ts; the CLK-021/022 duplicate IDs are renumbered 021a/022a here (021b/022b live in tests/money — the stamping side). CLK-018/019/020 (applyConversion) moved: 018's "unknown email = unresolved" survives in tests/imports/test_commit.py; 019 (consolidate_as) and 020 (rate_proportion) are phase-outs and were deliberately NOT ported (06 §1 dropped list).""" from app.services.imports.clockify import ( detect_date_format, format_date_range_label, parse_clockify_csv, parse_date_only, parse_duration_seconds, parse_time_only, split_client_project, ) # ---------------------------------------------------------------- dates def test_clk_001_parses_iso(): assert parse_date_only("2026-05-20", "YYYY-MM-DD") == "2026-05-20" assert parse_date_only("2026-1-5", "YYYY-MM-DD") == "2026-01-05" def test_clk_002_parses_mmdd_with_us_selector(): assert parse_date_only("5/20/2026", "MM/DD/YYYY") == "2026-05-20" assert parse_date_only("12/2/2025", "MM/DD/YYYY") == "2025-12-02" def test_clk_003_ddmm_selector_differs_from_us(): assert parse_date_only("2/12/2025", "DD/MM/YYYY") == "2025-12-02" assert parse_date_only("2/12/2025", "MM/DD/YYYY") == "2025-02-12" def test_clk_004_null_on_garbage(): assert parse_date_only("not a date", "YYYY-MM-DD") is None assert parse_date_only("", "MM/DD/YYYY") is None def test_clk_005_rejects_out_of_range(): assert parse_date_only("2026-13-01", "YYYY-MM-DD") is None assert parse_date_only("2026-02-32", "YYYY-MM-DD") is None assert parse_date_only("13/01/2026", "MM/DD/YYYY") is None def test_clk_006_two_digit_years_are_2000s(): assert parse_date_only("5/20/26", "MM/DD/YYYY") == "2026-05-20" assert parse_date_only("20/5/26", "DD/MM/YYYY") == "2026-05-20" # ---------------------------------------------------------------- times def test_clk_007_parses_24h(): assert parse_time_only("13:45:30", "24h") == "13:45:30" assert parse_time_only("0:00:00", "24h") == "00:00:00" assert parse_time_only("9:05", "24h") == "09:05:00" def test_clk_008_parses_12h_with_meridiem(): assert parse_time_only("1:45:30 PM", "12h") == "13:45:30" assert parse_time_only("1:45:30 am", "12h") == "01:45:30" def test_clk_009_noon_and_midnight(): assert parse_time_only("12:00:00 AM", "12h") == "00:00:00" assert parse_time_only("12:00:00 PM", "12h") == "12:00:00" assert parse_time_only("12:30:00 AM", "12h") == "00:30:00" assert parse_time_only("12:30:00 PM", "12h") == "12:30:00" def test_clk_010_null_on_garbage(): assert parse_time_only("25:00:00", "24h") is None assert parse_time_only("", "24h") is None assert parse_time_only("13:45:30 PM", "12h") is None # 13 with PM def test_clk_026_24h_regardless_of_fmt_arg(): assert parse_time_only("14:22:07", "12h") == "14:22:07" assert parse_time_only("14:22:07", "24h") == "14:22:07" assert parse_time_only("14:22:07") == "14:22:07" def test_clk_027_12h_regardless_of_fmt_arg(): assert parse_time_only("2:22:07 PM", "24h") == "14:22:07" assert parse_time_only("2:22:07 PM", "12h") == "14:22:07" assert parse_time_only("2:22:07 PM") == "14:22:07" def test_clk_028_plain_low_hour_is_24h_not_garbage(): assert parse_time_only("1:45:30", "12h") == "01:45:30" assert parse_time_only("1:45:30") == "01:45:30" # ------------------------------------------------------ format detection def test_clk_029_iso_on_four_digit_year_prefix(): assert detect_date_format(["2026-05-20", "2026-05-21"]) == "YYYY-MM-DD" def test_clk_030_ddmm_when_any_first_slot_over_12(): assert detect_date_format(["1/5/2026", "25/05/2026", "1/2/2026"]) == "DD/MM/YYYY" def test_clk_031_mmdd_when_any_second_slot_over_12(): assert detect_date_format(["5/20/2026", "6/1/2026", "1/2/2026"]) == "MM/DD/YYYY" def test_clk_032_null_when_nothing_parses(): assert detect_date_format([]) is None assert detect_date_format(["gibberish", "also gibberish"]) is None def test_clk_032b_tightest_span_week_is_ddmm(): # Real failure mode 2026-06-09 (the "26-01-08" batch): every # day-of-month <= 12 scattered 132 June entries across 8 months. week = ["01/06/2026", "02/06/2026", "03/06/2026", "05/06/2026", "08/06/2026"] assert detect_date_format(week) == "DD/MM/YYYY" def test_clk_032c_tightest_span_us_weekly_export(): week = ["06/01/2026", "06/02/2026", "06/03/2026", "06/05/2026", "06/08/2026"] assert detect_date_format(week) == "MM/DD/YYYY" def test_clk_032d_null_when_spans_equal(): assert detect_date_format(["1/2/2026", "2/1/2026"]) is None def test_clk_033_ignores_blank_and_unparseable(): assert detect_date_format(["", " ", "gibberish", "25/05/2026"]) == "DD/MM/YYYY" def test_clk_034_mixed_iso_and_numeric_first_signal_wins(): out = detect_date_format(["2026-05-20", "25/05/2026"]) assert out in ("YYYY-MM-DD", "DD/MM/YYYY") # ----------------------------------------------------- date-range labels def test_clk_040_same_month_range(): assert ( format_date_range_label({"min": "2026-06-02", "max": "2026-06-08"}) == "Jun 2 – Jun 8, 2026" ) def test_clk_041_cross_month_same_year(): assert ( format_date_range_label({"min": "2026-05-28", "max": "2026-06-03"}) == "May 28 – Jun 3, 2026" ) def test_clk_042_cross_year_shows_both_years(): assert ( format_date_range_label({"min": "2025-12-28", "max": "2026-01-03"}) == "Dec 28, 2025 – Jan 3, 2026" ) def test_clk_043_single_day(): assert format_date_range_label({"min": "2026-06-02", "max": "2026-06-02"}) == "Jun 2, 2026" def test_clk_044_null_in_null_out(): assert format_date_range_label(None) is None # ------------------------------------------------------------- durations def test_clk_011_parses_hms(): assert parse_duration_seconds("1:00:00") == 3600 assert parse_duration_seconds("0:01:30") == 90 assert parse_duration_seconds("5:20:36") == 5 * 3600 + 20 * 60 + 36 def test_clk_012_parses_hm(): assert parse_duration_seconds("1:30") == 90 * 60 assert parse_duration_seconds("0:30") == 30 * 60 def test_clk_013_parses_decimal_hours(): assert parse_duration_seconds("1.5") == 5400 assert parse_duration_seconds("0.25") == 900 assert parse_duration_seconds("5.34") == round(5.34 * 3600) def test_clk_013b_null_for_empty_or_nonsense(): assert parse_duration_seconds("") is None assert parse_duration_seconds("forever") is None # ------------------------------------------------------------- whole-CSV HEADER = ( "Project,Client,Description,Task,User,Group,Email,Tags,Billable," "Start Date,Start Time,End Date,End Time,Duration (h),Duration (decimal)," "Billable Rate (USD),Billable Amount (USD)" ) FIELD_ORDER = ( "Project", "Client", "Description", "Task", "User", "Group", "Email", "Tags", "Billable", "Start Date", "Start Time", "End Date", "End Time", "Duration (h)", "Duration (decimal)", "Billable Rate (USD)", "Billable Amount (USD)", ) DEFAULTS = { "Project": "Test Project", "Client": "Test Client", "Description": "Something", "Task": "", "User": "Test User", "Group": "", "Email": "TEST@example.com", "Tags": "", "Billable": "Yes", "Start Date": "5/20/2026", "Start Time": "9:00:00 AM", "End Date": "5/20/2026", "End Time": "10:30:00 AM", "Duration (h)": "1:30:00", "Duration (decimal)": "1.5", "Billable Rate (USD)": "14", "Billable Amount (USD)": "21.00", } def row(**overrides: str) -> str: fields = {**DEFAULTS, **overrides} return ",".join(fields[key] for key in FIELD_ORDER) def test_clk_014_one_entry_per_non_empty_row(): csv = "\n".join([HEADER, row(), row(Description="Other")]) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") assert len(r.entries) == 2 assert r.errors == [] assert r.entries[0].start_at == "2026-05-20 09:00:00" assert r.entries[0].end_at == "2026-05-20 10:30:00" assert r.entries[0].duration_seconds == 5400 assert r.entries[0].billable is True # CSV "Client" goes into `operator`; CSV "Project" gets split. assert r.entries[0].operator == "Test Client" assert r.entries[0].project == "Test Project" assert r.entries[0].client is None def test_clk_021a_split_client_project_on_first_separator(): assert split_client_project("Foo : Bar") == ("Foo", "Bar") assert split_client_project("Foo : Bar : Baz") == ("Foo", "Bar : Baz") assert split_client_project("NoColon") == (None, "NoColon") # no surrounding spaces — strict " : " separator assert split_client_project("Foo:Bar") == (None, "Foo:Bar") def test_clk_022a_csv_level_split_of_project_field(): csv = "\n".join( [HEADER, row(Project="DaxTech : Website"), row(Project="PromptVictoria")] ) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") assert r.entries[0].client == "DaxTech" assert r.entries[0].project == "Website" assert r.entries[1].client is None assert r.entries[1].project == "PromptVictoria" def test_clk_015_reports_missing_required_headers(): bad = "Project,Client,Description\nA,B,C" r = parse_clockify_csv(bad, "MM/DD/YYYY", "12h") assert r.entries == [] assert "missing required columns" in r.errors[0]["message"].lower() def test_clk_016_unique_emails_and_date_range(): csv = "\n".join( [ HEADER, row(Email="a@x.com", **{"Start Date": "5/20/2026"}), row(Email="b@x.com", **{"Start Date": "5/22/2026"}), row(Email="a@x.com", **{"Start Date": "5/18/2026"}), ] ) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") assert r.unique_emails == ["a@x.com", "b@x.com"] assert r.date_range == {"min": "2026-05-18", "max": "2026-05-22"} def test_clk_017_emails_lowercased(): csv = "\n".join([HEADER, row(Email="Mixed.Case@EXAMPLE.com")]) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") assert r.entries[0].source_user_email == "mixed.case@example.com" # ------------------------------------------------- rebuild-only behavior def test_imp_009_no_toggl_alias_mapping(): """T-IMP-009 (port*): the Toggl dialect is retired (judgment #8) — Member/Stop date/Stop time headers do NOT satisfy the required set.""" toggl_header = ( "Project,Client,Description,Email,Member,Start date,Start time," "Stop date,Stop time,Duration" ) toggl_row = "A,B,C,d@x.com,M,2026-05-20,09:00,2026-05-20,10:00,1:00:00" r = parse_clockify_csv(toggl_header + "\n" + toggl_row) assert r.entries == [] assert "missing required columns" in r.errors[0]["message"].lower() # ... while the Clockify default layout passes (same required set) ok = parse_clockify_csv("\n".join([HEADER, row()])) assert len(ok.entries) == 1 and ok.errors == [] def test_imp_010_billable_boolean_variants(): csv = "\n".join( [ HEADER, row(Billable="yes"), row(Billable="TRUE"), row(Billable="1"), row(Billable="y"), row(Billable="no"), ] ) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") assert [e.billable for e in r.entries] == [True, True, True, True, False] def test_imp_011_invalid_start_skips_with_error_invalid_end_warns(): csv = "\n".join( [ HEADER, row(**{"Start Date": "garbage"}), row(**{"End Time": "99:99"}), ] ) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") # invalid START: row skipped, exact legacy error format assert len(r.entries) == 1 assert r.errors[0]["message"] == "Row 2: invalid start date/time (garbage 9:00:00 AM)" # invalid END: row kept, end nulled — and SURFACED (rebuild fixes wart #1) assert r.entries[0].end_at is None assert any("invalid end date/time" in w["message"] for w in r.warnings) assert r.total_rows == 2 def test_imp_030_ambiguous_weekly_csv_lands_in_one_month(): """The "26-01-08" incident regression: a fully-ambiguous DD/MM weekly CSV parsed with the MM/DD fallback still lands in ONE month because the tightest-span detector overrides the fallback.""" days = ["01/06/2026", "02/06/2026", "03/06/2026", "05/06/2026", "08/06/2026"] csv = "\n".join([HEADER] + [row(**{"Start Date": d, "End Date": d}) for d in days]) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") # wrong fallback on purpose months = {e.start_at[:7] for e in r.entries} assert months == {"2026-06"} assert r.date_format_used == "DD/MM/YYYY" def test_blank_lines_skipped_and_total_rows_counts_data_rows(): csv = "\n".join([HEADER, row(), "", row(), ""]) r = parse_clockify_csv(csv, "MM/DD/YYYY", "12h") assert len(r.entries) == 2 assert r.total_rows == 2 # T-IMP-029's numerator: parsed-entry basis