From 695e4211faae961efa0f8a314dad1cfd024f5e39 Mon Sep 17 00:00:00 2001 From: tallison Date: Mon, 26 Oct 2026 17:43:13 -0400 Subject: [PATCH] TIKA-5002: parse PEM-armored CMS/PKCS7 like DER --- CHANGES.txt | 8 ++ .../org/apache/tika/mime/tika-mimetypes.xml | 3 +- .../tika/parser/crypto/CmsClassifier.java | 118 ++++++++++++++++++ .../tika/parser/crypto/Pkcs7Parser.java | 41 +++--- .../tika/detect/crypto/Pkcs7DetectorTest.java | 19 ++- .../tika/parser/crypto/PemFixtures.java | 43 +++++++ .../parser/crypto/Pkcs7DetectionTest.java | 3 + .../tika/parser/crypto/Pkcs7ParserTest.java | 85 ++++++++++++- 8 files changed, 296 insertions(+), 24 deletions(-) create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-crypto-module/src/test/java/org/apache/tika/parser/crypto/PemFixtures.java diff --git a/CHANGES.txt b/CHANGES.txt index c5b945e6de5..e36c8e43b2c 100644 --- a/CHANGES.txt +++ b/CHANGES.txt @@ -1,3 +1,11 @@ +Release 4.2.1 - ??? + + OTHER CHANGES + + * PEM-armored CMS/PKCS7 (-----BEGIN PKCS7----- or -----BEGIN CMS-----) is parsed like + DER: Pkcs7Parser and the opt-in pkcs-7-detector report the smime-type and extract + signed content; -----BEGIN CMS----- is now detected (TIKA-5002). + Release 4.2.0 - 10/25/2026 BREAKING CHANGES AND DEPRECATIONS diff --git a/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml b/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml index dda5383b430..37be9a47b75 100644 --- a/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml +++ b/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml @@ -921,8 +921,9 @@ - + +