leptris 1.9.292.0-ppc64le-linux → 1.9.302.0-ppc64le-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: deba2902336772763d8daf6c1bf66cf6381a1c1536b83a7ea604f27fd6dd8e2f
-  data.tar.gz: 52c284c22ac8ebc747410589daf061afbb8dcfd9e900ce3fec0f45110d190d97
+  metadata.gz: 2764954457c94ab3a836428d2e5fbe63235ce201e99c92446573030d489e1b6a
+  data.tar.gz: 33f05143b2d66134a8261bdb45665b800eec9a5edcca3f455d6f4249c47901b6
 SHA512:
-  metadata.gz: 7eaa86daa077f9c4ef1adcf01e78340d744ba6c9f73a5bb30fdd16de4efc3cb5dfb75fee50912c348f332ac545aba7422497b1fa92e47d6c685d8b4c6fd44c11
-  data.tar.gz: 6ae7b5c085e442ce31d94391da70fb4db563b38af1b91275cc0bb5087bdb1d5ee840965c9dcc8501f1fec7e31067dd23e63bfa0a804d32968edd4e2cb883da75
+  metadata.gz: abfce50cca667748bb0fee5e17aa61e1980d298238c94a431075fc3d8e5b4fd1f574c2915c7a5990b868822d3e98bbc1980c192430187213695020a65484f7c0
+  data.tar.gz: 2d1a21dd0b38bf9aab1a407eda3d21614c606037c23c5444fc3ea0ac6d500636151c49c4f950a4d374da540938c05c0c83c32e6f38087cb45d49c01b1986cb98

data/CHANGELOG.md

@@ -1,3 +1,26 @@
+## [1.9.302.0] - 2026-10-05
+
+### Engine sync (libleptris 1.9.293-1.9.302)
+
+Ten upstream releases ride in this pin — internal fixes and
+performance with NO binding-surface changes (zero header deltas
+292..302; the audit gate confirms 363/362 unchanged). Highlights:
+
+- **XQuery correctness**: a false() bound anywhere read as truthy;
+  fn:not uses the effective boolean value; fn:abs(()) is empty;
+  string lt/gt are codepoint comparisons; fn:avg edge shapes;
+  aggregates atomize array arguments; `instance of xs:integer`
+  demands integrality; xs:byte/unsignedByte/unsignedInt
+  constructors; fn:sum#2's zero argument.
+- **Collation**: UCA over the vendored DUCET table (slices 1-4) —
+  fn:normalize-unicode F&O conformance, collation-aware string
+  functions, 71+1078 QT3 cases adopted, implicit weights and
+  alternate=blanked.
+- **Performance**: per-thread recycle of mutation blocks (DOM
+  create/build/free).
+- **Rust bindings**: first tokenless crates.io release (leptris
+  v1.4.1) from CI.
+
 ## [1.9.292.0] - 2026-10-03
 
 ### Fixed

data/Rakefile

@@ -8,7 +8,7 @@ RSpec::Core::RakeTask.new(:spec)
 # Pin for `rake compile` and the platform-gem builds. Keep in lockstep
 # with .github/workflows/build.yml (which calls `rake compile`) and the
 # CHANGELOG when libleptris releases.
-LIBLEPTRIS_VERSION = "1.9.292"
+LIBLEPTRIS_VERSION = "1.9.302"
 # Vendored alongside libleptris for fn:normalize-unicode (TODO
 # .restructure/20): built per platform with a RELOCATABLE @rpath
 # install name, loaded by ffi.rb before libleptris so the

data/lib/leptris/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Leptris
-  VERSION = "1.9.292.0"
+  VERSION = "1.9.302.0"
 end

data/vendor-src/README.md

@@ -1,7 +1,7 @@
 Sources vendored in this gem (recompile rights; the ruby
 variant builds them at install via extconf.rb):
 
-- libleptris v1.9.292
+- libleptris v1.9.302
 - utf8proc v2.11.0
 
 Rebuild by hand:

data/vendor-src/libleptris/CHANGELOG.md

@@ -1,5 +1,336 @@
 ## [Unreleased]
 
+## [1.9.302] - 2026-10-04
+
+### Added
+
+- **XQuery: aggregates atomize array arguments** — `fn:avg`,
+  `fn:sum`, `fn:min` and `fn:max` take `xs:anyAtomicType*`, so a
+  dense array argument now contributes its members instead of
+  leaking the internal carrier: `avg([1,2,3,4,5])` = 3,
+  `sum([1,2,3,4,5])` = 15 (fn-avg-10, fn-sum-11, fn-min-19,
+  fn-max-19). A new shared decoder turns carriers keyed exactly
+  1..n into positional members, recursing into nested arrays
+  (`[[1,2],[3]]` → 1,2,3); maps and sparse carriers stay single
+  items, and `item()`-typed functions such as `fn:count` still see
+  an array as one item, per XDM. `fn:sum`'s per-item accumulation
+  moved into a helper so atomized members feed the existing
+  int64-exact and xs:float channels unchanged.
+- **XQuery: `instance of` over the integer family demands
+  integrality** — `xs:integer` and its derived types
+  (int/long/short/byte/unsigned*/nonNegative…) now require an
+  integral value on both the sequence-member and scalar paths:
+  `fn:abs(1.1) instance of xs:integer` is false,
+  `fn:abs(-3) instance of xs:integer` is true.
+
+### Fixed
+
+- **XQuery: `fn:avg` edge shapes** — `avg(())` returns the empty
+  sequence under XQuery (XPath 1.0 parity untouched), and averages
+  over `xs:yearMonthDuration` format through the shared months
+  formatter (cbcl-avg-006: `P1Y`). Also freed a nested-array
+  carrier on an allocation-failure path in the atomizing decoder.
+- QT3 re-pins from one verified run: fn/avg 164→173, fn/max
+  165→167, fn/min 165→167, fn/sum 203→204 (+14 adopted cases;
+  total pins 1134 → 1148; 61/61 suites green).
+
+
+
+## [1.9.301] - 2026-10-04
+
+### Fixed
+
+- **XQuery: a false() bound anywhere read as truthy** — values
+  stringified to a marker-less "false" that every effective-boolean-
+  value site saw as a non-empty string, so `let $x := false() return
+  if ($x)...` took the then-branch and fold accumulators ignored a
+  false() zero (fold-left-004). Variable bindings, local:function
+  thunk arguments and the fold accumulators/items now carry the
+  boolean type marker; the EBV read honors it on singleton synthetic
+  members (XML 1.0 forbids raw control characters in text content,
+  so the marker cannot collide with document data); named-reference
+  closure calls spell marked booleans back to literals; both string
+  consumers render them as true/false. (PR #1522)
+
+- **fn:not uses the effective boolean value** — not(false()) is
+  true while fn:empty((false())) stays false; real nodes keep the
+  XPath 1.0 existence rule, so libxml2 parity is unchanged.
+  (PR #1522)
+
+- **fn:abs(()) is the empty sequence** under the XQuery surface;
+  **fn:sum((), $zero) returns a non-numeric zero verbatim**
+  (sum((), xs:dayTimeDuration("PT0S")) = PT0S); **fn:avg over
+  dayTimeDurations** divides the total seconds and formats
+  (fn-avg-4: PT5H30M); and the kept lexical zero in fn:sum is freed
+  on every result path (a Linux ASAN catch — macOS has no leak
+  sanitizer). (PR #1522)
+
+
+
+## [1.9.300] - 2026-10-04
+
+### Added
+
+- **XQuery: the xs:float and int64 typed-atom channels survive the
+  numeric function hop (+49 QT3 agreements; the fifteen-family batch
+  pins rise 1078→1127 and fn:round is fully green at 220/220)**.
+  fn:abs, fn:round, fn:round-half-to-even and the avg/min/max
+  aggregates copy the float tag onto their results (round over
+  xs:float("3.4028235E38") spells 3.4028235E38, not the widened
+  double digits); fn:sum keeps an exact long-long total when every
+  member is an integer lexical (fn:sum#2's zero seeds it); fn:floor,
+  fn:ceiling, fn:round and fn:abs pass int64 atoms through unchanged
+  (floor(xs:integer("999999999999999999")) stays exact, not 1e18).
+  (PR #1520)
+
+- **xs:byte, xs:unsignedByte and xs:unsignedInt constructors** —
+  the three integer subtypes were unregistered and errored as
+  unknown functions. (PR #1520)
+
+### Fixed
+
+- **is_int results now also carry the double field** — eq and
+  boolean() comparisons read number_value, which the int64 path
+  left unset (sum((3,4,5)) eq 12 was false). (PR #1520)
+
+- **The float-precision speller snaps into the float domain before
+  spelling** — double arithmetic can leave a non-float-representable
+  value whose shortest float round-trip never terminates, spelling
+  18-digit mantissas. (PR #1520)
+
+
+
+## [1.9.299] - 2026-10-04
+
+### Added
+
+- **XQuery: 1078 QT3 cases adopted across fifteen fn families** —
+  the numeric aggregates and rounding set (abs, avg, ceiling, floor,
+  max, min, round, round-half-to-even, sum) plus the higher-order
+  combiners (apply, filter, for-each, for-each-pair, fold-left,
+  fold-right), vendored verbatim from the upstream QT3 mirror. The
+  named per-suite excludes document the typed-atom lane's remaining
+  levers (xs:float spelling through aggregates, int64-exact
+  multi-argument sums, instance-of results). (PR #1518)
+
+- **fn:sum#2** — the zero argument returns its value for the empty
+  sequence: fn:sum((1,2,3), 10) = 16, fn:sum((), 5) = 5.
+  (PR #1518)
+
+### Fixed
+
+- **Number spelling destroyed integral magnitudes** — the shared
+  trailing-zero trim ran on dot-free integer renderings, so 1e18
+  spelled "1"; it now runs only when a decimal point is present.
+  Negative zero also spells "-0" (fn:round(-0.01) = -0), and
+  fn:round preserves -0 for inputs in (-0.5, 0). (PR #1518)
+
+- **Value carriers overflowed at DBL_MAX** — the ext31 string
+  carrier used the libxml2-parity printer, which renders DBL_MAX
+  with 18 significant digits; strtod read-back of that string
+  overflows to infinity, so fn:avg((1.7976931348623157E308)) was
+  INF. Carriers now use the injective shortest-round-trip spelling.
+  (PR #1518)
+
+- **fn:sum rejected non-nodeset arguments** — single-item sequences
+  (passed as scalars by the XQuery adapter) errored out. (PR #1518)
+
+- **fn:round()/fn:round-half-to-even(()) now return the empty
+  sequence** under the XQuery surface; XPath 1.0 coercion stays NaN
+  (libxml2 parity unchanged). (PR #1518)
+
+- **fn:max/fn:min over non-numeric items** (xs:string, xs:anyURI)
+  compare in codepoint order and return the extreme item instead of
+  coercing to zero. (PR #1518)
+
+- **QT3 runner: the standard `emptydoc`/`empty` environments
+  resolve to the empty context** — cases carrying them were
+  silently skipped (the abs/ceiling/floor/fold-* families adopted
+  zero cases before this). (PR #1518)
+
+
+
+## [1.9.298] - 2026-10-04
+
+### Added
+
+- **XPath/XQuery: the six remaining string functions honor UCA
+  collations (DUCET lane closed)** — starts-with, ends-with,
+  contains, substring-before, substring-after and deep-equal now
+  route `http://www.w3.org/2013/collation/UCA` URIs through the
+  collation module. Matching scans codepoint-aligned windows under
+  the collation compare (every collation-unit boundary falls
+  between codepoints, so the scan is exact across contractions and
+  normalization); substring-before/after slice the leftmost-shortest
+  occurrence. deep-equal threads the collation into plain string
+  atoms and map values, while \x03-marked carriers keep their
+  value-space equality. **QT3 adoption rises by 73 cases**:
+  contains 46→63, starts-with 43→56, ends-with 34→48,
+  substring-before 12→26, substring-after 16→29, deep-equal
+  221→223. (PR #1515)
+
+- **Collation: UCA 7.1.1 implicit weights** — codepoints with no
+  DUCET mapping sort by the two-CE algorithm: the registered
+  @implicitweights ranges (Tangut/Tangut-Supplement base FB00,
+  Khitan FB02, Nushu FB01) order ahead of the unassigned groups
+  (base 0xFB80 + 2*(cp>>15)), each codepoint emitting an
+  even/odd CE pair that orders within its group by codepoint.
+  (PR #1515)
+
+- **Collation: `alternate=blanked`** (fn-contains-35..38) — the
+  third W3C UCA variable-weighting value is accepted, and variable
+  collation elements now leave every ordinary level under
+  shifted/blanked weighting (shifted retains its quaternary
+  re-add; blanked drops them wholly — ICU variable semantics).
+  (PR #1515)
+
+- **CLI: `leptris xslt` command** — apply a stylesheet to a
+  document and print the serialized result tree:
+  `leptris xslt -s style.xsl input.xml`. Conventions match
+  xsltproc: INPUT is a file path, `-` or absent reads stdin. The
+  stylesheet compiles via leptris_xslt_parse_file, so
+  xsl:include/xsl:import resolve relative to the sheet. New
+  CLI_ERROR_XSLT exit code (7). (PR #1516)
+
+- **CLI: man pages for every command** — new leptris-xslt.1 plus
+  the missing leptris-xquery.1, leptris-diff.1 and
+  leptris-validate.1, all registered for generation. (PR #1516)
+
+### Fixed
+
+- **CLI: `--help` was missing registered commands** — the usage
+  text hand-maintained its own command list, so the registered
+  `diff` and `xquery` commands were invisible. The help listing
+  now iterates the command registry (the descriptors are the
+  single source of truth), and adding a command can no longer
+  leave help stale. xquery's private stream reader is promoted to
+  shared cli_read_stream/cli_read_file. (PR #1516)
+
+
+
+## [1.9.297] - 2026-10-03
+
+### Fixed
+
+- **XQuery: string lt/gt are codepoint value comparisons** — the
+  shared XPath 1.0 comparison numeric-coerced strings, so two
+  collation-keys that both spell numbers compared as equal numbers.
+  Both comparison sites now codepoint-compare string operands when
+  the evaluation is XQuery-flavored (the evaluator's string branch
+  and the VM twin); XPath 1.0 evaluation is unchanged.
+  (PR #1513)
+
+- **XQuery: fn:codepoints-to-string encodes every item of its
+  sequence argument** — the collector collapsed a parenthesized
+  sequence to one scalar (its space-joined spelling), so
+  (37, 65500, 37) encoded as just the first codepoint. Collation-key
+  adoption rises to 12/56 run-and-agree. (PR #1513)
+
+
+
+## [1.9.296] - 2026-10-03
+
+### Added
+
+- **XPath/XQuery: 71 QT3 collation cases adopted (DUCET slice 4)** —
+  the misc/UCACollation corpus (62 cases: the UCA ordering battery
+  over DUCET weights) and fn/collation-key (9 cases). The collation
+  URI grammar now parses the W3C semicolon-separated parameter form,
+  accepts lang= (DUCET is the root locale), and applies
+  caseFirst=upper|lower by swapping the DUCET case tertiaries.
+  fn:collation-key gains its 1-argument form (the static default
+  collation; codepoint keys are the UTF-8 bytes) and its keys are
+  lowercase hex — injective AND order-preserving, so lt/gt on two
+  keys is byte-wise key order. The QT3 runner now credits an
+  error alternative inside any-of for a failed evaluation, gates the
+  optional simple-uca-fallback feature (this engine raises FOCH0002
+  per the strict F&O reading), and lifts the pre-DUCET
+  collation/UCA exclusion under a DUCET build. (PR #1511)
+
+### Fixed
+
+- the DUCET implicit-weight fallback dropped a mask that broke
+  ordering between high codepoints. (PR #1511)
+
+
+
+## [1.9.295] - 2026-10-03
+
+### Added
+
+- **XPath: collation-aware functions over the vendored DUCET
+  (slices 2-3)** — fn:compare's 3-argument form honors its collation
+  URI (unknown needed collations raise FOCH0002; unknown-but-unneeded
+  ones are ignored per the QT3 any-of expectations);
+  fn:collation-key($key, $collation) is new, returning the UCA sort
+  key as base64 text (the result-type enum is ABI-frozen with no
+  binary kind; base64 is injective, so key equality is byte equality);
+  fn:index-of, fn:distinct-values and fn:sort route plain-string
+  comparisons through the collation while typed atoms keep their
+  value-space equality. DUCET-gated: builds without utf8proc keep the
+  previous behavior. (PRs #1508, #1509)
+
+
+
+## [1.9.294] - 2026-10-03
+
+### Added
+
+- **XPath: UCA collation over the vendored DUCET table (slice 1)** —
+  `http://www.w3.org/2013/collation/UCA` collation URIs parse
+  `strength` and `alternate` parameters per F&O 3.x (defaults:
+  tertiary, non-ignorable) and compare through multi-level sort keys:
+  NFD (utf8proc) → DUCET weights (Unicode 16.0.0, 38,443 single
+  codepoints + 964 contractions, vendored with an offline table
+  generator) → primary/secondary/tertiary levels with 0x00
+  separators; `alternate=shifted` demotes variable primaries to the
+  quaternary level. Codepoint and html-ascii-case-insensitive
+  collations keep their semantics. Unmapped codepoints get a coarse
+  deterministic fallback (the full UCA 7.1.1 implicit-weight
+  algorithm is a later slice). New CMake option
+  `LEPTRIS_ENABLE_DUCET` (default on, requires utf8proc; builds
+  without utf8proc degrade to codepoint collation). Function
+  wiring (fn:compare, fn:collation-key, default collation) and
+  QT3 UCA case adoption are the next slices. (PR #1506)
+
+- **XQuery: fn:normalize-unicode F&O conformance** — the
+  single-argument form normalizes with NFC instead of returning the
+  input unchanged; unknown normalization forms raise FOCH0003
+  instead of silently falling back to NFC; the form argument is
+  case-insensitive with surrounding whitespace tolerated
+  (FULLY-NORMALIZED is gone from F&O 3.x; its satisfied="false"
+  twins run). utf8proc-gated end to end; the 29-run
+  fn/normalize-unicode QT3 family is adopted. (PR #1505)
+
+### Fixed
+
+- DUCET builds without utf8proc (cppcheck leg, Rust lane, ILP32,
+  Windows static) degrade to codepoint collation with a warning
+  instead of failing the configure. (PR #1506)
+
+
+
+## [1.9.293] - 2026-10-03
+
+### Performance
+
+- DOM: per-thread recycle of mutation blocks. Document create/build/free
+  cycles now park their elem (45KB), name (4KB) and attr (5KB) blocks on
+  thread-local free-lists instead of returning them to malloc — the next
+  cycle carves from hot pages instead of re-faulting fresh ones. Byte-capped
+  (8MB elem, 4MB name/attr); POSIX threads drain via a pthread_key
+  destructor at thread exit, and `leptris_explicit_cleanup()` drains
+  synchronously. Mutation doc-cycle row: 19.4 → 15.1 ns/child (−22%), gap
+  to pugixml on that shape narrows 1.66x → 1.29x. Single-document append
+  throughput is unchanged. (PR #1503)
+
+### Rust bindings
+
+- First fully tokenless crates.io release: leptris v1.4.1 published from CI
+  via crates.io Trusted Publishing (`rust-lang/crates-io-auth-action` —
+  cargo itself has no native OIDC support). The Rust release lane now needs
+  no registry token of any kind. (PRs #1497, #1499–#1502)
+
 ## [1.9.292] - 2026-10-02
 
 ### Added

data/vendor-src/libleptris/CMakeLists.txt

@@ -3,7 +3,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(leptris
-    VERSION 1.9.292
+    VERSION 1.9.302
     DESCRIPTION "Fast XML parser and XPath evaluator in pure C"
     LANGUAGES C CXX
 )
@@ -30,6 +30,7 @@ option(LEPTRIS_BUILD_MAN_PAGES "Generate man pages with asciidoctor" OFF)
 option(LEPTRIS_BUILD_BENCHMARKS "Build performance benchmarks" OFF)
 option(LEPTRIS_ENABLE_UTF8PROC "Enable Unicode support via utf8proc" ON)
 option(LEPTRIS_ENABLE_ICONV "Enable encoding conversion via iconv" ON)
+option(LEPTRIS_ENABLE_DUCET "Vendor DUCET table for UCA collation (requires utf8proc)" ON)
 option(LEPTRIS_ENABLE_ASAN "Enable AddressSanitizer (catches heap bugs at runtime)" OFF)
 option(LEPTRIS_ENABLE_FUZZING "Build libFuzzer harness" OFF)
 option(LEPTRIS_BUILD_DOCS "Build Doxygen API docs" OFF)
@@ -341,6 +342,10 @@ if(LEPTRIS_BUILD_CLI AND LEPTRIS_BUILD_MAN_PAGES)
         cli/man/leptris-parse.1.adoc
         cli/man/leptris-xpath.1.adoc
         cli/man/leptris-format.1.adoc
+        cli/man/leptris-validate.1.adoc
+        cli/man/leptris-diff.1.adoc
+        cli/man/leptris-xquery.1.adoc
+        cli/man/leptris-xslt.1.adoc
     )
 
     foreach(ADOC_SOURCE ${ADOC_MAN_SOURCES})

data/vendor-src/libleptris/benchmarks/modification/bench_append_attr_pugixml.cpp

@@ -44,6 +44,42 @@ int main(void) {
                (t1 - t0) / N_APPEND);
     }
 
+    /* ---- mut-doc-cycle: 20k create/build/free cycles, 1024
+     * children each (1 elem block + ~7 name blocks per cycle). The
+     * mut-block recycle target: without it every cycle frees those
+     * blocks back to malloc (madvise) and the next cycle re-mallocs
+     * and re-faults them on the carve memsets. */
+    const int N_CYCLE = 20000;
+    const int CYCLE_CHILDREN = 1024;
+    {
+        double t0 = now_ns();
+        for (int i = 0; i < N_CYCLE; i++) {
+            LeptrisDocument d = leptris_document_create();
+            LeptrisElement root = leptris_element_create(d, "root");
+            leptris_document_set_root(d, root);
+            for (int c = 0; c < CYCLE_CHILDREN; c++) {
+                LeptrisElement e = leptris_element_create(d, "c");
+                leptris_element_append_child(root, e);
+            }
+            leptris_document_free(d);
+        }
+        double t1 = now_ns();
+        printf("mutcycle leptris: %7.1f ns/child\n",
+               (t1 - t0) / ((double)N_CYCLE * CYCLE_CHILDREN));
+    }
+    {
+        double t0 = now_ns();
+        for (int i = 0; i < N_CYCLE; i++) {
+            pugi::xml_document d;
+            pugi::xml_node root = d.append_child("root");
+            for (int c = 0; c < CYCLE_CHILDREN; c++)
+                root.append_child("c");
+        }
+        double t1 = now_ns();
+        printf("mutcycle pugixml: %7.1f ns/child\n",
+               (t1 - t0) / ((double)N_CYCLE * CYCLE_CHILDREN));
+    }
+
     /* ---- attr-parse: parse 20k docs, 4 elems x 16 attrs ---- */
     std::string xml = "<r>";
     for (int e = 0; e < 4; e++) {

data/vendor-src/libleptris/bindings/rust/Cargo.lock

@@ -4,4 +4,4 @@ version = 4
 
 [[package]]
 name = "leptris"
-version = "1.4.0"
+version = "1.4.1"

data/vendor-src/libleptris/bindings/rust/Cargo.toml

@@ -1,10 +1,12 @@
 [package]
 name = "leptris"
-version = "1.4.0"
+version = "1.4.1"
 edition = "2021"
 description = "Rust bindings for libleptris — fast XML 1.0 parsing, XPath 1.0, SAX"
 license = "MIT"
 readme = "README.md"
+repository = "https://github.com/leptris/leptris"
+homepage = "https://www.leptris.org"
 links = "leptris"
 build = "build.rs"
 

data/vendor-src/libleptris/cli/CLI_ARCHITECTURE.md

@@ -73,7 +73,7 @@ The Leptris CLI is a **thin layer** on top of the C library API (`libleptris`).
 
 Every aspect of the CLI follows MECE principles:
 
-- **Commands**: Each command has distinct responsibility (parse, xpath, format, version)
+- **Commands**: Each command has distinct responsibility (parse, validate, xpath, format, diff, xquery, xslt, version — the registry is the single source of truth for this list and for --help)
 - **Options**: Three exclusive sources (CLI → ENV → Default)
 - **Output formats**: Three formats (XML, JSON, text), never mixed
 - **Error levels**: Three levels (warning, error, fatal), no overlap

data/vendor-src/libleptris/cli/CMakeLists.txt

@@ -14,6 +14,7 @@ add_executable(leptris-cli
     commands/xpath.c
     commands/format.c
     commands/xquery.c
+    commands/xslt.c
 )
 
 # Link to libleptris. When both static and shared are built, link the

data/vendor-src/libleptris/cli/cli.c

@@ -5,6 +5,7 @@
 
 #include "cli.h"
 #include "error.h"
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 
@@ -89,7 +90,6 @@ cli_command_t* cli_registry_find(
 void cli_registry_print_all(const cli_registry_t* registry) {
     if (!registry) return;
 
-    printf("Available commands:\n");
     for (size_t i = 0; i < registry->count; i++) {
         printf("  %-12s  %s\n",
             registry->commands[i]->name,
@@ -97,6 +97,40 @@ void cli_registry_print_all(const cli_registry_t* registry) {
     }
 }
 
+/* ------------------------------------------------------------------------- */
+/* Shared Command Utilities                                                  */
+/* ------------------------------------------------------------------------- */
+
+char* cli_read_stream(FILE* fp, size_t* out_len) {
+    size_t cap = 4096, len = 0;
+    char* buf = (char*)malloc(cap);
+    if (!buf) return NULL;
+    for (;;) {
+        size_t n = fread(buf + len, 1, cap - len - 1, fp);
+        len += n;
+        if (len + 1 >= cap) {
+            cap *= 2;
+            char* grown = (char*)realloc(buf, cap);
+            if (!grown) { free(buf); return NULL; }
+            buf = grown;
+            continue;
+        }
+        break;
+    }
+    buf[len] = 0;
+    if (out_len) *out_len = len;
+    return buf;
+}
+
+char* cli_read_file(const char* path, size_t* out_len) {
+    if (strcmp(path, "-") == 0) return cli_read_stream(stdin, out_len);
+    FILE* fp = fopen(path, "rb");
+    if (!fp) return NULL;
+    char* s = cli_read_stream(fp, out_len);
+    fclose(fp);
+    return s;
+}
+
 /* ------------------------------------------------------------------------- */
 /* Helper Functions                                                          */
 /* ------------------------------------------------------------------------- */
@@ -110,6 +144,7 @@ const char* cli_result_to_string(cli_result_t result) {
         case CLI_ERROR_ARGS:    return "invalid arguments";
         case CLI_ERROR_MEMORY:  return "memory allocation failed";
         case CLI_ERROR_INTERNAL: return "internal error";
+        case CLI_ERROR_XSLT:    return "xslt error";
         default:                return "unknown error";
     }
 }

data/vendor-src/libleptris/cli/cli.h

@@ -17,6 +17,7 @@
 #define LEPTRIS_CLI_H
 
 #include <stddef.h>
+#include <stdio.h>
 
 #ifdef __cplusplus
 extern "C" {
@@ -43,7 +44,8 @@ typedef enum {
     CLI_ERROR_IO = 3,       /**< I/O error (file not found, etc.) */
     CLI_ERROR_ARGS = 4,     /**< Invalid arguments */
     CLI_ERROR_MEMORY = 5,   /**< Memory allocation failed */
-    CLI_ERROR_INTERNAL = 6  /**< Internal error (bug) */
+    CLI_ERROR_INTERNAL = 6, /**< Internal error (bug) */
+    CLI_ERROR_XSLT = 7      /**< XSLT transformation failed */
 } cli_result_t;
 
 /* ------------------------------------------------------------------------- */
@@ -166,12 +168,39 @@ cli_command_t* cli_registry_find(
 /**
  * Print all registered commands
  *
- * Used for global --help output.
+ * Prints one aligned "name — description" line per registered
+ * command, in registration order, without a section header — the
+ * caller frames the listing. This is the single source of truth
+ * for the global --help command list: command descriptors carry
+ * their own description, and no hand-maintained copy of the list
+ * exists anywhere else.
  *
  * @param registry Registry to print
  */
 void cli_registry_print_all(const cli_registry_t* registry);
 
+/* ------------------------------------------------------------------------- */
+/* Shared Command Utilities                                                  */
+/* ------------------------------------------------------------------------- */
+
+/**
+ * Read a whole stream into a NUL-terminated heap buffer
+ *
+ * @param fp Stream to read (not closed)
+ * @param out_len Length in bytes excluding the NUL, or NULL
+ * @return Buffer (caller frees), or NULL on allocation failure
+ */
+char* cli_read_stream(FILE* fp, size_t* out_len);
+
+/**
+ * Read a whole file into a NUL-terminated heap buffer
+ *
+ * @param path File path, or "-" for stdin
+ * @param out_len Length in bytes excluding the NUL, or NULL
+ * @return Buffer (caller frees), NULL on open or allocation failure
+ */
+char* cli_read_file(const char* path, size_t* out_len);
+
 /* ------------------------------------------------------------------------- */
 /* Standard Commands (Forward Declarations)                                 */
 /* ------------------------------------------------------------------------- */
@@ -225,6 +254,14 @@ extern cli_command_t* cli_command_validate(void);
  */
 extern cli_command_t* cli_command_xquery(void);
 
+/**
+ * Get the 'xslt' command
+ *
+ * Command: leptris xslt -s STYLESHEET [INPUT]
+ * Purpose: Apply an XSLT stylesheet to an XML document
+ */
+extern cli_command_t* cli_command_xslt(void);
+
 #ifdef __cplusplus
 }
 #endif