daniel543x/pdfcraft
1
0 Fork 0
mirror of https://github.com/storytold/pdfcraft.git synced 2026-11-07 03:01:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

M8: phone pattern finds slashed and labelled unseparated numbers (#3205)

Browse Source 
Italian documents write landlines with a slash between area code and
number (0426/123456), and mobiles without separators (3451234567,
+393451234567). The phone pattern needed a separator other than a slash,
so these stayed readable after redaction.

- A slash joins two digits in a number with a trunk-0 area code; a
  North American or + number with a slash still doesn't match, so
  reference numbers like 2024/123456 stay unmarked.
- A number without separators matches only right after a phone label
  (Tel., cell., Fax:, telefono, mobile, ...). Unlabelled runs of digits
  (ids, VAT numbers) still don't match.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Gv2WwdgjmBz33GWkwgNn3Q
This commit is contained in:
mtlcl410andClaude Opus 5.5 committed 2026-10-18 19:37:27 +08:00
1 parent 50f261d70c
commit 73aea6e0ac
2 files changed
+106 -9
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

parity/acrobat-features.toml
+2 -2
View File
@@ -5608,8 +5608,8 @@ milestone = "M8"
status = "shipped"
commands = ["redact.search"]
tools = ["redact_mark"]
evidence = ["crates/redact/src/patterns.rs::phone_numbers", "crates/redact/src/patterns.rs::credit_cards_need_a_valid_checksum", "crates/automation/tests/automation.rs::redacting_through_tools"]
notes = "phone (North American, E.164 with + country code, national with trunk 0), e-mail, credit card (Luhn), SSN, dates (English US forms); text drawn in a font whose built-in encoding we hold no table for (Symbol, ZapfDingbats, MacExpert) has no Unicode mapping, so a pattern search cannot see it -- it is skipped rather than mis-decoded"
evidence = ["crates/redact/src/patterns.rs::phone_numbers", "crates/redact/src/patterns.rs::slashed_and_labelled_unseparated_phone_numbers", "crates/redact/src/patterns.rs::credit_cards_need_a_valid_checksum", "crates/automation/tests/automation.rs::redacting_through_tools"]
notes = "phone (North American, E.164 with + country code, national with trunk 0, a slash after a trunk-0 area code; numbers without separators only after a phone label such as Tel. or cell.), e-mail, credit card (Luhn), SSN, dates (English US forms); text drawn in a font whose built-in encoding we hold no table for (Symbol, ZapfDingbats, MacExpert) has no Unicode mapping, so a pattern search cannot see it -- it is skipped rather than mis-decoded"
[[feature]]
id = "protect.redact-pattern-locales"