* refactor(tuning): prune dormant runtime knobs Remove unused tuning controls and adaptive search budget state. Extract testable ONNX slot reconciliation and search telemetry hydration seams, and correct the Apple Silicon sysctl value width. * refactor(vector): retire dormant backends Remove unused FAISS, model-infrastructure, VectorIndexManager, and TurboQuant paths while keeping Simeon PQ and float-vector storage. Migrate unused V2.2 quantized schemas transactionally to V2.3. Databases containing non-default quantized formats or packed-code blobs fail closed with recovery guidance and no mutation. * refactor(plugins): remove legacy SDK tooling Remove the Ghidra and SDK submodules, their bespoke tests, and stale scan exclusions. Retain generic PluginProcess coverage against the repository mock fixture. * build(vector): remove stale FAISS overrides * refactor(ipc): remove dormant FSM snapshots * refactor(ingest): unify bounded KG enqueue * fix(plugins): harden allocation contracts Keep ABI outputs null or fully initialized when allocations fail, and represent empty object payloads without relying on malloc(0). * fix(storage): define empty object reads Return a null buffer with zero length for successful empty-object reads instead of treating malloc(0) as an allocation contract. * refactor(storage): trim through string views * test: prune dormant harness helpers Remove unused readiness and fixture helpers, and keep benchmark client-count doubling in a wide integer domain. * chore(cpp): initialize analyzer-facing locals * build(simeon): advance analyzer cleanup * refactor(config): drop dead daemon client keys * refactor(ipc): inject daemon client transport Socket and in-process execution now share DaemonClient request dispatch, so CLI fallbacks do not need alternate service paths. * refactor(retrieval): route CLI through daemon Search and grep now use the same daemon handlers over socket or in-process transport. Live grep remains an explicit freshness inspection. * refactor(graph): move CLI scope into daemon Graph CLI requests now share daemon handlers across socket and in-process transports. CWD filtering occurs before pagination so scoped totals and pages stay correct. * build: isolate test-only runtime controls * refactor(metadata): decouple lock telemetry * fix(services): return on request timeout * fix(retrieval): enforce workspace scope * fix(graph): scope nodes before pagination * fix(grep): drop binary result lines * fix(daemon): bound checkpoint wait * fix(repair): use KG health checks * fix(storage): always verify compressed CRC * perf(vector): skip unchanged PQ snapshots * build(zyp): exclude bench from default build * build: protect Meson files from formatter * refactor: remove unreachable production APIs * refactor(daemon): remove dormant runtime state * fix(vector): harden daemon provider calls Timed-out coroutines must own their client and requests. Provider discovery must also fail instead of returning synthetic embeddings in production. * refactor(storage): remove unusable adapters * fix(cli): unify in-process add requests * fix(tsan): preserve async worker progress * test(cli): isolate daemon-dependent suites * fix(repair): expose queue backoff progress
223 lines
7 KiB
Meson
223 lines
7 KiB
Meson
#zyp - Zig YAMS PDF Extractor
|
|
#High - performance PDF text extraction using zpdf(https: // github.com/Lulzx/zpdf)
|
|
|
|
if not get_option ('plugin-zyp')
|
|
subdir_done()
|
|
endif
|
|
|
|
if host_machine.system() == 'darwin' and get_option('b_coverage')
|
|
warning('Skipping zyp plugin in macOS coverage builds: Clang gcov runtime cannot link with the zyp bundle/benchmark.')
|
|
subdir_done()
|
|
endif
|
|
|
|
#Find Zig compiler(requires 0.15.x; zpdf is not Zig 0.16 - compatible yet)
|
|
zig = find_program('zig', required: false)
|
|
if not zig.found()
|
|
warning('Zig compiler not found, skipping zyp plugin. Install Zig 0.15.x to enable.')
|
|
subdir_done()
|
|
endif
|
|
|
|
zig_version_result = run_command(zig, 'version', check: false)
|
|
if zig_version_result.returncode() != 0
|
|
warning('Unable to determine Zig version, skipping zyp plugin.')
|
|
subdir_done()
|
|
endif
|
|
|
|
zig_version = zig_version_result.stdout().strip()
|
|
if not zig_version.version_compare('>=0.15.0')
|
|
warning('Zig @0@ is unsupported by zyp; zpdf requires Zig 0.15+. Skipping zyp plugin.'.format(zig_version))
|
|
subdir_done()
|
|
endif
|
|
|
|
#Platform - specific library name and rpath
|
|
if host_machine.system() == 'darwin'
|
|
zpdf_lib_name = 'libzpdf.dylib'
|
|
#@loader_path is used for shared libraries / modules to find libs in same directory
|
|
zyp_install_rpath = '@loader_path'
|
|
zyp_link_args = ['-fno-sanitize=thread']
|
|
elif host_machine.system() == 'windows'
|
|
zpdf_lib_name = 'zpdf.dll'
|
|
zpdf_import_lib_name = 'zpdf.lib'
|
|
zyp_install_rpath = '' # Windows doesn't use rpath
|
|
#Link against dynamic CRT libraries; avoid static CRT conflict
|
|
zyp_link_args = [
|
|
'/NODEFAULTLIB:libcmt',
|
|
'/NODEFAULTLIB:libcmtd',
|
|
'msvcrt.lib',
|
|
'vcruntime.lib',
|
|
'ucrt.lib',
|
|
]
|
|
else
|
|
zpdf_lib_name = 'libzpdf.so'
|
|
#$ORIGIN refers to directory containing the loading module
|
|
zyp_install_rpath = '$ORIGIN'
|
|
zyp_link_args = ['-fno-sanitize=thread']
|
|
endif
|
|
|
|
#Build zpdf shared library via Zig and copy to build directory
|
|
#Zig outputs DLLs to zpdf / zig - out / bin / on Windows, shared libs to zig - out / lib / on Unix
|
|
zpdf_src_dir = meson.current_source_dir() / 'zpdf'
|
|
if host_machine.system() == 'windows'
|
|
#Windows : DLL goes to bin /, import lib goes to lib /
|
|
zpdf_lib_src = zpdf_src_dir / 'zig-out' / 'bin' / zpdf_lib_name
|
|
zpdf_import_lib_src = zpdf_src_dir / 'zig-out' / 'lib' / zpdf_import_lib_name
|
|
else
|
|
zpdf_lib_src = zpdf_src_dir / 'zig-out' / 'lib' / zpdf_lib_name
|
|
endif
|
|
zpdf_build_dir = meson.current_build_dir()
|
|
fs = import('fs')
|
|
if not fs.exists(zpdf_src_dir / 'build.zig')
|
|
warning('zpdf source not found (missing build.zig), skipping zyp plugin build.')
|
|
subdir_done()
|
|
endif
|
|
|
|
#Platform - specific build command
|
|
if host_machine.system() == 'windows'
|
|
#Windows : Use PowerShell for build
|
|
#Build zpdf and copy both DLL and import lib to build directory
|
|
zpdf_lib = custom_target('zpdf_shared',
|
|
command: [
|
|
'powershell', '-NoProfile', '-Command',
|
|
'Push-Location "@0@"; & "@1@" build -Doptimize=ReleaseFast; Copy-Item "@2@" "@3@\\@4@"; Copy-Item "@5@" "@3@\\@6@"; Pop-Location'.format(
|
|
zpdf_src_dir,
|
|
zig.full_path(),
|
|
zpdf_lib_src,
|
|
zpdf_build_dir,
|
|
zpdf_lib_name,
|
|
zpdf_import_lib_src,
|
|
zpdf_import_lib_name
|
|
)
|
|
],
|
|
output: [zpdf_lib_name, zpdf_import_lib_name],
|
|
build_by_default: true,
|
|
console: true,
|
|
)
|
|
#Extract just the import library for linking
|
|
zpdf_import_lib = zpdf_lib[1]
|
|
elif host_machine.system() == 'darwin'
|
|
zpdf_build_command = (
|
|
'cd "@0@" && "@1@" build -Doptimize=ReleaseFast -Dtarget=@2@-macos.${MACOSX_DEPLOYMENT_TARGET:-26.0} && cp "@3@" "@4@/@5@"'
|
|
).format(
|
|
zpdf_src_dir,
|
|
zig.full_path(),
|
|
host_machine.cpu_family(),
|
|
zpdf_lib_src,
|
|
zpdf_build_dir,
|
|
zpdf_lib_name
|
|
)
|
|
zpdf_lib = custom_target('zpdf_shared',
|
|
command: [
|
|
'sh', '-c', zpdf_build_command
|
|
],
|
|
output: [zpdf_lib_name],
|
|
build_by_default: true,
|
|
console: true,
|
|
)
|
|
else
|
|
#Unix(Linux / macOS) : Use shell
|
|
zpdf_lib = custom_target('zpdf_shared',
|
|
command: [
|
|
'sh', '-c',
|
|
'cd "@0@" && "@1@" build -Doptimize=ReleaseFast && cp "@2@" "@3@/@4@"'.format(
|
|
zpdf_src_dir,
|
|
zig.full_path(),
|
|
zpdf_lib_src,
|
|
zpdf_build_dir,
|
|
zpdf_lib_name
|
|
)
|
|
],
|
|
output: [zpdf_lib_name],
|
|
build_by_default: true,
|
|
console: true,
|
|
)
|
|
endif
|
|
|
|
#Create a dependency object that includes the zpdf library
|
|
#Use build_rpath for build - time, install_rpath handles installed location
|
|
if host_machine.system() == 'windows'
|
|
#On Windows, link against the import library only(not the DLL)
|
|
#Use sources to establish build dependency, but link via explicit path
|
|
zpdf_dep = declare_dependency(
|
|
link_args: [zpdf_build_dir / zpdf_import_lib_name],
|
|
sources: [zpdf_import_lib], # Build dependency on just the import lib
|
|
)
|
|
else
|
|
zpdf_dep = declare_dependency(
|
|
link_args: ['-L' + zpdf_build_dir, '-lzpdf'],
|
|
sources: [zpdf_lib], # This creates the build dependency
|
|
)
|
|
endif
|
|
|
|
#Compiler - specific flags for this plugin.
|
|
zyp_cpp_args = []
|
|
if meson.get_compiler('cpp').get_id() != 'msvc'
|
|
zyp_cpp_args = ['-std=c++20', '-fno-sanitize=thread']
|
|
endif
|
|
|
|
#Plugin sources
|
|
zyp_sources = files(
|
|
'zyp_plugin.cpp',
|
|
'zpdf_wrapper.cpp',
|
|
'pdf_metadata.cpp',
|
|
)
|
|
|
|
#Build the plugin(minimal dependencies - no spdlog to avoid TSan conflicts)
|
|
zyp_plugin = shared_module('yams_zyp',
|
|
zyp_sources,
|
|
include_directories: [
|
|
include_directories('../../include'),
|
|
include_directories('.'),
|
|
],
|
|
dependencies: [zpdf_dep],
|
|
cpp_args: zyp_cpp_args,
|
|
link_args: zyp_link_args,
|
|
#build_rpath ensures the plugin can find libzpdf during build / test
|
|
build_rpath: zpdf_build_dir,
|
|
#install_rpath ensures the plugin can find libzpdf after installation
|
|
install_rpath: zyp_install_rpath,
|
|
build_by_default: true,
|
|
install: true,
|
|
install_dir: plugins_dir,
|
|
name_prefix: '',
|
|
)
|
|
|
|
#Install zpdf library alongside the plugin
|
|
#Use platform - specific install script
|
|
if host_machine.system() == 'windows'
|
|
meson.add_install_script('powershell', '-NoProfile', '-Command',
|
|
'$dest = if ($env:DESTDIR) { Join-Path $env:DESTDIR "@1@" } else { "@1@" }; New-Item -ItemType Directory -Force -Path $dest | Out-Null; Copy-Item -Path "@0@" -Destination $dest'.format(
|
|
zpdf_build_dir / zpdf_lib_name,
|
|
get_option('prefix') / plugins_dir
|
|
)
|
|
)
|
|
else
|
|
meson.add_install_script('sh', '-c',
|
|
'mkdir -p "$DESTDIR@1@" && cp "@0@" "$DESTDIR@1@/"'.format(
|
|
zpdf_build_dir / zpdf_lib_name,
|
|
get_option('prefix') / plugins_dir
|
|
)
|
|
)
|
|
endif
|
|
|
|
#-- -- zyp extraction benchmark -- --
|
|
#Measures sequential vs parallel PDF extraction throughput.
|
|
#Usage : zyp_extraction_bench < pdf_path>[repeat_count]
|
|
zyp_extraction_bench_sources = files(
|
|
'../../tests/benchmarks/zyp_extraction_bench.cpp',
|
|
'zpdf_wrapper.cpp',
|
|
)
|
|
|
|
zyp_extraction_bench = executable('zyp_extraction_bench',
|
|
zyp_extraction_bench_sources,
|
|
include_directories: [
|
|
include_directories('../../include'),
|
|
include_directories('../..'),
|
|
include_directories('.'),
|
|
],
|
|
dependencies: [zpdf_dep],
|
|
cpp_args: zyp_cpp_args,
|
|
build_rpath: zpdf_build_dir,
|
|
build_by_default: false,
|
|
install: false,
|
|
override_options: ['b_sanitize=none'],
|
|
)
|