P3: the IIF in plain ASCII with every change listed, and the CPA package as of one day (defects 7, 21)
The CPA package's general-journal.iif now holds every posted entry through as_of (closing entries left out, D-36), written as plain ASCII with CR LF, DOCNUM the entry id, QuickBooks Desktop's field limits and subaccount types honoured, and every character written differently listed in the export's warnings and the README (grouped by substitution, TINs masked). The 1099 worksheet stops at as_of too. PDFs print CJK, Arabic, Hebrew, Thai and Devanagari (Noto fallbacks, OFL), and so does the viewer. has_full_tin reads Unicode separators. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01T3gXMVt7XJPi6ens1or9Dj
This commit is contained in:
48 files changed
+5661
-317
No files matched your search
@@ -365,6 +365,7 @@ fn a_shared_payment_counts_the_vendors_share() {
|
||||
&s.l,
|
||||
2026,
|
||||
None,
|
||||
None,
|
||||
&ledger_core::PaymentAccounts {
|
||||
cash: vec![bank],
|
||||
financing: vec![],
|
||||
|
||||
@@ -177,7 +177,7 @@ fn has_full_tin_truth_table() {
|
||||
("291\u{2013}12\u{2013}2846", true), // en dashes
|
||||
("291\u{a0}12\u{a0}2846", true), // no-break spaces
|
||||
("12 3456789", false), // four separators break the run: 2 + 7
|
||||
("571, 93, 2846", false), // a comma is not a separator
|
||||
("291, 12, 2846", false), // a comma is not a separator
|
||||
("12\t3456789", false), // a tab is not a space
|
||||
("12345678", false), // eight digits
|
||||
("123-45-678", false),
|
||||
@@ -241,6 +241,145 @@ fn has_full_tin_unicode_digits() {
|
||||
assert!(has_full_tin("١٢٣٤٥٦٧٨٩")); // Arabic-Indic digits
|
||||
}
|
||||
|
||||
/// Oracle: `has_full_tin` doc (P3 review round 2): past ASCII, every form
|
||||
/// of the five separators Unicode has separates (every Zs space, every
|
||||
/// Dash character, the compatibility forms of the dot, slash and
|
||||
/// underscore; `docs/spec/sources/unicode-tin-text.md`, Unicode 17.0),
|
||||
/// and invisible characters (Default_Ignorable_Code_Point) don't count
|
||||
/// toward the gap. A TIN typed in fullwidth forms, Arabic-Indic digits,
|
||||
/// with an en dash, a non-breaking hyphen, a Hebrew maqaf, any space, or
|
||||
/// with right-to-left marks around its hyphens is still a full TIN; line
|
||||
/// breaks, commas and a fourth visible separator still end a run.
|
||||
/// (Before, "１２３－４５－６７８９" passed: the fullwidth hyphen-minus wasn't
|
||||
/// a separator, nor the ideographic or thin space.)
|
||||
#[test]
|
||||
fn has_full_tin_reads_every_script_and_separator() {
|
||||
let tins = [
|
||||
// Fullwidth digits and hyphen-minus.
|
||||
"\u{FF11}\u{FF12}\u{FF13}\u{FF0D}\u{FF14}\u{FF15}\u{FF0D}\u{FF16}\u{FF17}\u{FF18}\u{FF19}",
|
||||
"291\u{FF0D}12\u{FF0D}2846", // fullwidth hyphen-minus
|
||||
"291\u{FE63}12\u{FE63}2846", // small hyphen-minus
|
||||
// Arabic-Indic, Extended Arabic-Indic, Devanagari (en dashes).
|
||||
"\u{661}\u{662}\u{663}-\u{664}\u{665}-\u{666}\u{667}\u{668}\u{669}",
|
||||
"\u{6F1}\u{6F2}\u{6F3}\u{6F4}\u{6F5}\u{6F6}\u{6F7}\u{6F8}\u{6F9}",
|
||||
"\u{967}\u{968}\u{969}\u{2013}\u{96A}\u{96B}\u{2013}\u{96C}\u{96D}\u{96E}\u{96F}",
|
||||
"291\u{2013}12\u{2013}2846", // en dash
|
||||
"291\u{2011}12\u{2011}2846", // non-breaking hyphen
|
||||
"291\u{2012}12\u{2012}2846", // figure dash
|
||||
"291\u{2015}12\u{2015}2846", // horizontal bar
|
||||
"291\u{5BE}12\u{5BE}2846", // Hebrew maqaf
|
||||
"291\u{301C}12\u{301C}2846", // wave dash
|
||||
"291\u{A0}12\u{A0}2846", // no-break space
|
||||
"291\u{3000}12\u{3000}2846", // ideographic space
|
||||
"291\u{2009}12\u{2009}2846", // thin space
|
||||
"291\u{202F}12\u{202F}2846", // narrow no-break space
|
||||
"291 \u{2014} 12 \u{2014} 2846", // three: space, em dash, space
|
||||
"291\u{FF0E}12\u{FF0E}2846", // fullwidth full stop
|
||||
"291\u{2024}12\u{2024}2846", // one dot leader
|
||||
"291\u{FF0F}12\u{FF0F}2846", // fullwidth solidus
|
||||
"291\u{FF3F}12\u{FF3F}2846", // fullwidth low line
|
||||
// Zero-width spaces between every digit.
|
||||
"2\u{200B}9\u{200B}1\u{200B}1\u{200B}2\u{200B}2\u{200B}8\u{200B}4\u{200B}6",
|
||||
"291\u{200F}-\u{200F}12\u{200F}-\u{200F}2846", // right-to-left marks around hyphens
|
||||
"291\u{200E}\u{200E}\u{200E}\u{200E} 12 2846", // invisible marks don't count
|
||||
"291\u{AD}12\u{AD}2846", // soft hyphens
|
||||
"291\u{2060}122846", // word joiner
|
||||
"\u{FEFF}291122846",
|
||||
];
|
||||
for t in tins {
|
||||
assert!(has_full_tin(t), "has_full_tin({t:?})");
|
||||
let masked = redact_full_tins(t);
|
||||
assert!(!has_full_tin(&masked), "{t:?} masked: {masked:?}");
|
||||
assert_eq!(
|
||||
masked.chars().count(),
|
||||
t.chars().count(),
|
||||
"only digits change: {masked:?}"
|
||||
);
|
||||
}
|
||||
assert_eq!(
|
||||
redact_full_tins(
|
||||
"ref \u{FF11}\u{FF12}\u{FF13}\u{FF0D}\u{FF14}\u{FF15}\u{FF0D}\u{FF16}\u{FF17}\u{FF18}\u{FF19}"
|
||||
),
|
||||
"ref •••\u{FF0D}••\u{FF0D}••••"
|
||||
);
|
||||
assert_eq!(
|
||||
redact_full_tins("291\u{200F}-\u{200F}12-2846 ok"),
|
||||
"•••\u{200F}-\u{200F}••-•••• ok"
|
||||
);
|
||||
let not = [
|
||||
"12\u{3000}\u{3000}\u{3000}\u{3000}3456789", // four visible separators
|
||||
"12 \u{2014} \u{200B}-3456789", // four, an invisible one among them
|
||||
"291\u{2028}12\u{2028}2846", // line separators end a run
|
||||
"291\u{2029}12\u{2029}2846", // paragraph separators
|
||||
"291\u{85}12\u{85}2846", // next line
|
||||
"291\u{FF0C}12\u{FF0C}2846", // fullwidth commas
|
||||
"291\u{3001}12\u{3001}2846", // ideographic commas
|
||||
"\u{FF11}\u{FF12}\u{FF13}\u{FF14}\u{FF15}\u{FF16}\u{FF17}\u{FF18}", // eight digits
|
||||
"291\u{200B}12284", // eight, invisibly joined
|
||||
];
|
||||
for t in not {
|
||||
assert!(!has_full_tin(t), "has_full_tin({t:?})");
|
||||
}
|
||||
}
|
||||
|
||||
/// The reading before P3 review round 2, the oracle for ASCII: past it,
|
||||
/// only the no-break space and a few dashes separated, and every
|
||||
/// separator counted.
|
||||
fn has_full_tin_before(text: &str) -> bool {
|
||||
let sep = |c: char| {
|
||||
matches!(
|
||||
c,
|
||||
' ' | '-' | '.' | '/' | '_' | '\u{a0}' | '\u{2010}'..='\u{2014}' | '\u{2212}'
|
||||
)
|
||||
};
|
||||
let chars: Vec<char> = text.chars().collect();
|
||||
let mut i = 0;
|
||||
while i < chars.len() {
|
||||
if !chars[i].is_numeric() {
|
||||
i += 1;
|
||||
continue;
|
||||
}
|
||||
let (mut digits, mut last, mut j) = (1, i, i + 1);
|
||||
while j < chars.len() {
|
||||
if chars[j].is_numeric() {
|
||||
digits += 1;
|
||||
last = j;
|
||||
j += 1;
|
||||
continue;
|
||||
}
|
||||
let gap = chars[j..].iter().take_while(|c| sep(**c)).count();
|
||||
if (1..=3).contains(&gap) && chars.get(j + gap).is_some_and(|c| c.is_numeric()) {
|
||||
j += gap;
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
if digits >= 9 {
|
||||
return true;
|
||||
}
|
||||
i = last + 1;
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
proptest! {
|
||||
#![proptest_config(ProptestConfig::with_cases(2000))]
|
||||
|
||||
/// `has_full_tin` reads ASCII exactly as it did (the fix only widens
|
||||
/// what separates past ASCII), and what it found before in any text
|
||||
/// it still finds: it only ever finds more.
|
||||
#[test]
|
||||
fn has_full_tin_keeps_its_ascii_reading(
|
||||
ascii in "[0-9 ./_\t\n\r,:a-]{0,40}",
|
||||
any in "[0-9 ./_\t\n,a\u{A0}\u{2010}-\u{2015}\u{2212}\u{FF0D}\u{3000}\u{200B}\u{200F}\u{FF10}-\u{FF19}\u{660}-\u{669}\u{2028}-]{0,40}",
|
||||
) {
|
||||
prop_assert_eq!(has_full_tin(&ascii), has_full_tin_before(&ascii), "{:?}", ascii);
|
||||
if has_full_tin_before(&any) {
|
||||
prop_assert!(has_full_tin(&any), "{:?}", any);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------- check_text
|
||||
|
||||
/// Oracle: `check_text` doc: not a full TIN, at most 500 characters, no
|
||||
|
||||
Reference in new issue
Block a user