From 3863d520c10c8889759e5a6ccddd159a6b4e035e Mon Sep 17 00:00:00 2001
From: shlomsh <shlomsh@gmail.com>
Date: Tue, 15 Sep 2026 17:51:34 +0300
Subject: [PATCH] fix(pdf): bump pdf-inspector to 1.20.0 so RTL text extracts
 in logical order

pdf-inspector 1.14.2 emitted right-to-left runs in visual order, so Hebrew,
Arabic and Persian came out character-reversed. Fixed upstream in
pdf-inspector#440 and #441 (released in 1.16.0), but every published
anydoc-wasm still pinned 1.14.2. Closes #170.

The only snapshot that moves is pdf/text.pdf, and every change is an
improvement: "Persian with ZWNJ" now reads as written, the endnote marker
becomes a proper <sup>, and the table heading is grouped with its rows.
---
 Cargo.lock                                    | 221 +++++-------------
 Cargo.toml                                    |   2 +-
 tests/snapshots/snapshots__pdf__text.pdf.snap |   8 +-
 3 files changed, 64 insertions(+), 167 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 6bb48e2a..cf820d1b 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -10,13 +10,13 @@ checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
 
 [[package]]
 name = "aes"
-version = "0.8.4"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0"
+checksum = "f8eb277bec05f56a0e0591f155a484cbd0f4f07ff2905051a48c72f004f7ed58"
 dependencies = [
- "cfg-if",
  "cipher",
- "cpufeatures 0.2.17",
+ "cpubits",
+ "cpufeatures",
 ]
 
 [[package]]
@@ -28,6 +28,21 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "alloc-no-stdlib"
+version = "2.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc7bb162ec39d46ab1ca8c77bf72e890535becd1751bb45f64c597edb4c8c6b3"
+
+[[package]]
+name = "alloc-stdlib"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0e76a019e91224d279006ff972f1e984179a6e9feb050adba6ce8274aef23195"
+dependencies = [
+ "alloc-no-stdlib",
+]
+
 [[package]]
 name = "android_system_properties"
 version = "0.1.5"
@@ -99,7 +114,7 @@ dependencies = [
  "log",
  "pdf-inspector",
  "quick-xml",
- "sha2 0.11.0",
+ "sha2",
  "zip",
 ]
 
@@ -153,29 +168,30 @@ checksum = "b588b76d00fde79687d7646a9b5bdf3cc0f655e0bbd080335a95d7e96f3587da"
 
 [[package]]
 name = "block-buffer"
-version = "0.10.4"
+version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+checksum = "d2f6c7dbe95a6ed67ad9f18e57daf93a2f034c524b99fd2b76d18fdfeb6660aa"
 dependencies = [
- "generic-array",
+ "hybrid-array",
 ]
 
 [[package]]
-name = "block-buffer"
-version = "0.12.1"
+name = "block-padding"
+version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d2f6c7dbe95a6ed67ad9f18e57daf93a2f034c524b99fd2b76d18fdfeb6660aa"
+checksum = "710f1dd022ef4e93f8a438b4ba958de7f64308434fa6a87104481645cc30068b"
 dependencies = [
  "hybrid-array",
 ]
 
 [[package]]
-name = "block-padding"
-version = "0.3.3"
+name = "brotli-decompressor"
+version = "5.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a8894febbff9f758034a5b8e12d87918f56dfc64a8e1fe757d65e29041538d93"
+checksum = "3a32acac15fe1967bc3986b2a6347dffc965602354ea6f450ad07e8bfd253583"
 dependencies = [
- "generic-array",
+ "alloc-no-stdlib",
+ "alloc-stdlib",
 ]
 
 [[package]]
@@ -186,9 +202,9 @@ checksum = "72f5acc6cb2ba439de613abc23857ec3d78374d8ed5ac84e9d11336e87da8649"
 
 [[package]]
 name = "cbc"
-version = "0.1.2"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26b52a9543ae338f279b96b0b9fed9c8093744685043739079ce85cd58f289a6"
+checksum = "ce2dc9ee5f88d11e0beb842c88b33c8a5cf0d1329c4b19494af42b07dbfe8896"
 dependencies = [
  "cipher",
 ]
@@ -227,7 +243,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d524456ba66e72eb8b115ff89e01e497f8e6d11d78b70b1aa13c0fbd97540a81"
 dependencies = [
  "cfg-if",
- "cpufeatures 0.3.0",
+ "cpufeatures",
  "rand_core",
 ]
 
@@ -244,11 +260,11 @@ dependencies = [
 
 [[package]]
 name = "cipher"
-version = "0.4.4"
+version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "773f3b9af64447d2ce9850330c473515014aa235e6a783b02db81ff39e4a3dad"
+checksum = "e8cf2a2c93cd704877c0858356ed03480ff301ee950b43f1cbe4573b088bfa6c"
 dependencies = [
- "crypto-common 0.1.7",
+ "crypto-common",
  "inout",
 ]
 
@@ -291,13 +307,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
 
 [[package]]
-name = "cpufeatures"
-version = "0.2.17"
+name = "cpubits"
+version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
-dependencies = [
- "libc",
-]
+checksum = "15b85f9c39137c3a891689859392b1bd49812121d0d61c9caf00d46ed5ce06ae"
 
 [[package]]
 name = "cpufeatures"
@@ -342,16 +355,6 @@ version = "0.8.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "61803da095bee82a81bb1a452ecc25d3b2f1416d1897eb86430c6159ef717c17"
 
-[[package]]
-name = "crypto-common"
-version = "0.1.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
-dependencies = [
- "generic-array",
- "typenum",
-]
-
 [[package]]
 name = "crypto-common"
 version = "0.2.2"
@@ -419,38 +422,22 @@ dependencies = [
  "thiserror",
 ]
 
-[[package]]
-name = "deranged"
-version = "0.5.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7cd812cc2bc1d69d4764bd80df88b4317eaef9e773c75226407d9bc0876b211c"
-
-[[package]]
-name = "digest"
-version = "0.10.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
-dependencies = [
- "block-buffer 0.10.4",
- "crypto-common 0.1.7",
-]
-
 [[package]]
 name = "digest"
 version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f1dd6dbb5841937940781866fa1281a1ff7bd3bf827091440879f9994983d5c2"
 dependencies = [
- "block-buffer 0.12.1",
+ "block-buffer",
  "const-oid",
- "crypto-common 0.2.2",
+ "crypto-common",
 ]
 
 [[package]]
 name = "ecb"
-version = "0.1.2"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1a8bfa975b1aec2145850fcaa1c6fe269a16578c44705a532ae3edc92b8881c7"
+checksum = "26f2a8b3e564eba0877223dc343703ad0385794e882e6d13f3a4dd5c6b1f41ac"
 dependencies = [
  "cipher",
 ]
@@ -632,16 +619,6 @@ dependencies = [
  "slab",
 ]
 
-[[package]]
-name = "generic-array"
-version = "0.14.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
-dependencies = [
- "typenum",
- "version_check",
-]
-
 [[package]]
 name = "getrandom"
 version = "0.4.3"
@@ -732,12 +709,12 @@ dependencies = [
 
 [[package]]
 name = "inout"
-version = "0.1.4"
+version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "879f10e63c20629ecabbb64a8010319738c66a5cd0c29b02d63d272b03751d01"
+checksum = "4250ce6452e92010fdf7268ccc5d14faa80bb12fc741938534c58f16804e03c7"
 dependencies = [
  "block-padding",
- "generic-array",
+ "hybrid-array",
 ]
 
 [[package]]
@@ -773,12 +750,10 @@ dependencies = [
  "defmt",
  "jiff-core",
  "jiff-static",
- "jiff-tzdb-platform",
  "log",
  "portable-atomic",
  "portable-atomic-util",
  "serde_core",
- "windows-link",
 ]
 
 [[package]]
@@ -802,21 +777,6 @@ dependencies = [
  "syn 2.0.119",
 ]
 
-[[package]]
-name = "jiff-tzdb"
-version = "0.1.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "142bd39932ad231f10513df9ab62661fead8719872150b7ad02a2df79f4e141e"
-
-[[package]]
-name = "jiff-tzdb-platform"
-version = "0.1.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "875a5a69ac2bab1a891711cf5eccbec1ce0341ea805560dcd90b7a2e925132e8"
-dependencies = [
- "jiff-tzdb",
-]
-
 [[package]]
 name = "js-sys"
 version = "0.3.103"
@@ -858,12 +818,13 @@ checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
 
 [[package]]
 name = "lopdf"
-version = "0.42.0"
+version = "0.45.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "25aab26d99567469098e64a02f42679f8965c6401263eefa31d8f2dcc37a221c"
+checksum = "bfffda0fe1ab0157e1a13c14bebd3f28671f2fccb7922f0722ec53926e6922d3"
 dependencies = [
  "aes",
  "bitflags 2.13.1",
+ "brotli-decompressor",
  "cbc",
  "chrono",
  "ecb",
@@ -872,29 +833,26 @@ dependencies = [
  "getrandom",
  "indexmap",
  "itoa",
- "jiff",
  "log",
  "md-5",
  "nom",
  "rand",
  "rangemap",
  "rayon",
- "sha2 0.10.9",
+ "sha2",
  "stringprep",
  "thiserror",
- "time",
- "ttf-parser",
  "weezl",
 ]
 
 [[package]]
 name = "md-5"
-version = "0.10.6"
+version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf"
+checksum = "69b6441f590336821bb897fb28fc622898ccceb1d6cea3fde5ea86b090c4de98"
 dependencies = [
  "cfg-if",
- "digest 0.10.7",
+ "digest",
 ]
 
 [[package]]
@@ -985,12 +943,6 @@ dependencies = [
  "memchr",
 ]
 
-[[package]]
-name = "num-conv"
-version = "0.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "521739c6d2bac4aa25192232afe6841231376b2b26d4d9fae5ecf8ca5772e441"
-
 [[package]]
 name = "num-traits"
 version = "0.2.19"
@@ -1014,9 +966,9 @@ checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
 
 [[package]]
 name = "pdf-inspector"
-version = "1.14.2"
+version = "1.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e024ae242c514e2adf6aee186678e0eabdc2e5ecfbb2159186881b4498593cb"
+checksum = "dfa8858423125d0d4cf7bb249a4df85fbabb3bdcdb4dcfeadee9c4d13c762277"
 dependencies = [
  "env_logger",
  "include_dir",
@@ -1051,12 +1003,6 @@ dependencies = [
  "portable-atomic",
 ]
 
-[[package]]
-name = "powerfmt"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
-
 [[package]]
 name = "proc-macro2"
 version = "1.0.107"
@@ -1307,17 +1253,6 @@ dependencies = [
  "syn 3.0.3",
 ]
 
-[[package]]
-name = "sha2"
-version = "0.10.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
-dependencies = [
- "cfg-if",
- "cpufeatures 0.2.17",
- "digest 0.10.7",
-]
-
 [[package]]
 name = "sha2"
 version = "0.11.0"
@@ -1325,8 +1260,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "446ba717509524cb3f22f17ecc096f10f4822d76ab5c0b9822c5f9c284e825f4"
 dependencies = [
  "cfg-if",
- "cpufeatures 0.3.0",
- "digest 0.11.3",
+ "cpufeatures",
+ "digest",
 ]
 
 [[package]]
@@ -1425,36 +1360,6 @@ dependencies = [
  "syn 3.0.3",
 ]
 
-[[package]]
-name = "time"
-version = "0.3.55"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cdb87b95ec50ddfa440816d227a17b2ccbdda963a316a727fda0fc4334f7d134"
-dependencies = [
- "deranged",
- "num-conv",
- "powerfmt",
- "serde_core",
- "time-core",
- "time-macros",
-]
-
-[[package]]
-name = "time-core"
-version = "0.1.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9e1c906769ad99c88eaa54e728060edef082f8e358ff32030cb7c7d315e81109"
-
-[[package]]
-name = "time-macros"
-version = "0.2.32"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e689342a48d2ea927c87ea50cabf8594854bf940e9310208848d680d668ed85"
-dependencies = [
- "num-conv",
- "time-core",
-]
-
 [[package]]
 name = "tinyvec"
 version = "1.12.0"
@@ -1537,12 +1442,6 @@ dependencies = [
  "wasm-bindgen",
 ]
 
-[[package]]
-name = "version_check"
-version = "0.9.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
-
 [[package]]
 name = "wasm-bindgen"
 version = "0.2.126"
@@ -1600,9 +1499,9 @@ dependencies = [
 
 [[package]]
 name = "weezl"
-version = "0.1.12"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a28ac98ddc8b9274cb41bb4d9d4d5c425b6020c50c46f25559911905610b4a88"
+checksum = "d4ca08e5ef825b65b056d9efbd95c8750683f0a6d0466d02e96dc2e4e360f3d2"
 
 [[package]]
 name = "windows-core"
diff --git a/Cargo.toml b/Cargo.toml
index 2a334b72..895a23a7 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -27,7 +27,7 @@ csv = "1.4.0"
 flate2 = "1"
 encoding_rs = "0.8.35"
 log = "0.4"
-pdf-inspector = "1.14.2"
+pdf-inspector = "1.20.0"
 quick-xml = "0.41.0"
 zip = { version = "8.6.0", default-features = false, features = ["deflate"] }
 
diff --git a/tests/snapshots/snapshots__pdf__text.pdf.snap b/tests/snapshots/snapshots__pdf__text.pdf.snap
index 3df709dd..c72ed1f8 100644
--- a/tests/snapshots/snapshots__pdf__text.pdf.snap
+++ b/tests/snapshots/snapshots__pdf__text.pdf.snap
@@ -15,14 +15,12 @@ b)Alpha sub two
 i.Roman sub sub
 3.Third numbered Interrupting paragraph between lists.
 4.Fourth, continuing the count IV.Roman starting at four
-V.Roman five •Bullet one •Bullet two ◦Nested bullet
-## Table
-
-Wide head End Tall B2 C2 B3 C3
+V.Roman five •Bullet one •Bullet two ◦Nested bullet **Table** Wide head End Tall B2 C2
+B3 C3
 
 ## Notes and special text
 
-Music clef 𝄞 appears before this footnote¹ reference. i An endnote follows here. Persian with ZWNJ: مهاوخیم. Family emoji: 👨👩👧. Markdown specials: *stars* _under_ [bracket] `tick` #hash 1. dotted | pipe.
+Music clef 𝄞 appears before this footnote¹ reference. An endnote follows here<sup>i</sup>. Persian with ZWNJ: میخواهم. Family emoji: 👨👩👧. Markdown specials: *stars* _under_ [bracket] `tick` #hash 1. dotted | pipe.
 
 ## Links and anchors