pybcsv 1.5.11.dev0__tar.gz → 1.5.12__tar.gz

{pybcsv-1.5.11.dev0 → pybcsv-1.5.12}/CMakeLists.txt

@@ -159,3 +159,77 @@ target_compile_definitions(_bcsv PRIVATE BCSV_HAS_BATCH_CODEC=1)
 
 # ── Install ─────────────────────────────────────────────────────────────
 install(TARGETS _bcsv LIBRARY DESTINATION pybcsv)
+
+# ── Bundled CLI tools ───────────────────────────────────────────────────
+# A curated subset of the BCSV CLI tools is compiled into the wheel and
+# installed into the environment's scripts dir (on PATH in every venv), so
+# `pip install pybcsv` ships the high-performance converters with a version
+# that always matches the bundled library. Sources come from the parent
+# checkout (CI / full clone) or from the copies sync_headers.py places under
+# python/src/ for standalone sdist builds.
+option(PYBCSV_BUILD_TOOLS "Build and bundle the BCSV CLI tools" ON)
+
+set(PARENT_TOOLS_DIR  "${CMAKE_CURRENT_SOURCE_DIR}/../src/tools")
+set(LOCAL_TOOLS_DIR   "${CMAKE_CURRENT_SOURCE_DIR}/src/tools")
+set(PARENT_SHARED_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../src/shared")
+set(LOCAL_SHARED_DIR  "${CMAKE_CURRENT_SOURCE_DIR}/src/shared")
+
+if(EXISTS "${PARENT_TOOLS_DIR}/csv2bcsv.cpp")
+    set(BCSV_TOOLS_DIR  "${PARENT_TOOLS_DIR}")
+    set(BCSV_SHARED_DIR "${PARENT_SHARED_DIR}")
+elseif(EXISTS "${LOCAL_TOOLS_DIR}/csv2bcsv.cpp")
+    set(BCSV_TOOLS_DIR  "${LOCAL_TOOLS_DIR}")
+    set(BCSV_SHARED_DIR "${LOCAL_SHARED_DIR}")
+else()
+    set(BCSV_TOOLS_DIR "")
+endif()
+
+set(CLI11_INCLUDE_DIR "${BCSV_INCLUDE_DIR}/CLI11-2.6.2")
+
+if(PYBCSV_BUILD_TOOLS AND BCSV_TOOLS_DIR AND EXISTS "${CLI11_INCLUDE_DIR}/CLI11.hpp")
+    # Keep in sync with pybcsv/tools.py::TOOLS.
+    set(PYBCSV_TOOLS
+        csv2bcsv bcsv2csv bcsvHeader bcsvCast bcsvValidate
+        bcsvHead bcsvTail bcsvSampler bcsvCompare bcsvRepair bcsvGenerator)
+
+    # Compile the vendored LZ4 once, shared by every tool (the extension
+    # module compiles its own copy because nanobind owns that target).
+    add_library(pybcsv_tools_lz4 STATIC ${LZ4_SOURCES})
+    target_include_directories(pybcsv_tools_lz4 PUBLIC ${LZ4_DIR})
+
+    foreach(tool IN LISTS PYBCSV_TOOLS)
+        add_executable(${tool} "${BCSV_TOOLS_DIR}/${tool}.cpp")
+        target_include_directories(${tool} PRIVATE
+            ${CMAKE_CURRENT_BINARY_DIR}/include
+            ${BCSV_INCLUDE_DIR}
+            ${BCSV_TOOLS_DIR}
+            ${BCSV_SHARED_DIR}
+        )
+        target_include_directories(${tool} SYSTEM PRIVATE ${CLI11_INCLUDE_DIR})
+        target_link_libraries(${tool} PRIVATE pybcsv_tools_lz4)
+        target_compile_definitions(${tool} PRIVATE BCSV_HAS_BATCH_CODEC=1)
+        set_target_properties(${tool} PROPERTIES
+            CXX_STANDARD 20
+            CXX_STANDARD_REQUIRED ON
+        )
+        if(MSVC)
+            target_compile_options(${tool} PRIVATE /O2 /std:c++20)
+        elseif(APPLE)
+            target_compile_options(${tool} PRIVATE
+                -O3 -fexperimental-library -mmacosx-version-min=13.3)
+        else()
+            target_compile_options(${tool} PRIVATE -O3)
+            target_link_libraries(${tool} PRIVATE pthread)
+            target_link_options(${tool} PRIVATE -s)   # strip: ~60% smaller wheels
+        endif()
+    endforeach()
+
+    if(DEFINED SKBUILD_SCRIPTS_DIR)
+        install(TARGETS ${PYBCSV_TOOLS} RUNTIME DESTINATION "${SKBUILD_SCRIPTS_DIR}")
+    else()
+        install(TARGETS ${PYBCSV_TOOLS} RUNTIME DESTINATION bin)
+    endif()
+    message(STATUS "[pybcsv] Bundling CLI tools: ${PYBCSV_TOOLS}")
+else()
+    message(STATUS "[pybcsv] CLI tools not bundled (sources or CLI11 not found, or disabled)")
+endif()

{pybcsv-1.5.11.dev0 → pybcsv-1.5.12}/MANIFEST.in

@@ -17,4 +17,8 @@ prune tests
 prune examples
 global-exclude *.pyc
 global-exclude __pycache__
-global-exclude .DS_Store
+global-exclude .DS_Store
+# Bundled CLI tool sources (synced by sync_headers.py; compiled into the wheel)
+recursive-include src *.cpp
+recursive-include src *.h
+recursive-include src *.hpp

{pybcsv-1.5.11.dev0 → pybcsv-1.5.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pybcsv
-Version: 1.5.11.dev0
+Version: 1.5.12
 Summary: High-performance Python bindings for the BCSV (Binary CSV) library with pandas integration
 Keywords: csv,binary,data-science,compression,performance,pandas,numpy,big-data,data-processing
 Author-Email: Tobias Weber <weber.tobias.md@gmail.com>
@@ -156,6 +156,40 @@ with pybcsv.ReaderDirectAccess() as da:
     print(da.read(100))  # alternative syntax
 ```
 
+## Bundled Native CLI Tools
+
+The wheel ships the core BCSV command-line tools as native, version-matched
+binaries — installed into the environment's scripts directory, so they are on
+PATH in an activated venv with no compiler or CMake required:
+
+| Tool | Purpose |
+|------|---------|
+| `csv2bcsv` | CSV → BCSV with validated type inference (see the main CLI docs) |
+| `bcsv2csv` | BCSV → CSV with row/column selection |
+| `bcsvHeader` | Show a file's schema |
+| `bcsvHead` / `bcsvTail` | Show the first/last N rows |
+| `bcsvCast` | Change/narrow column types |
+| `bcsvSampler` | Filter/project rows with a condition expression |
+| `bcsvValidate` | Integrity-check a file |
+| `bcsvRepair` | Recover data from truncated/corrupted files |
+| `bcsvCompare` | Compare two files (with float tolerance) |
+| `bcsvGenerator` | Generate synthetic test datasets |
+
+```bash
+csv2bcsv data.csv data.bcsv        # from an activated environment
+```
+
+```python
+import pybcsv
+
+pybcsv.tools.run("csv2bcsv", "data.csv", "data.bcsv", "--overwrite")
+print(pybcsv.tools.run("bcsvHeader", "data.bcsv").stdout)
+pybcsv.tools.path("csv2bcsv")      # absolute path, e.g. for custom pipelines
+```
+
+Source builds can opt out with `-DPYBCSV_BUILD_TOOLS=OFF`; the full tool suite
+(and docs) live in the main repository under `src/tools/`.
+
 ## Parquet Conversion Tools (CLI)
 
 Installing `pybcsv` provides two streaming command-line converters (require the

{pybcsv-1.5.11.dev0 → pybcsv-1.5.12}/README.md

@@ -110,6 +110,40 @@ with pybcsv.ReaderDirectAccess() as da:
     print(da.read(100))  # alternative syntax
 ```
 
+## Bundled Native CLI Tools
+
+The wheel ships the core BCSV command-line tools as native, version-matched
+binaries — installed into the environment's scripts directory, so they are on
+PATH in an activated venv with no compiler or CMake required:
+
+| Tool | Purpose |
+|------|---------|
+| `csv2bcsv` | CSV → BCSV with validated type inference (see the main CLI docs) |
+| `bcsv2csv` | BCSV → CSV with row/column selection |
+| `bcsvHeader` | Show a file's schema |
+| `bcsvHead` / `bcsvTail` | Show the first/last N rows |
+| `bcsvCast` | Change/narrow column types |
+| `bcsvSampler` | Filter/project rows with a condition expression |
+| `bcsvValidate` | Integrity-check a file |
+| `bcsvRepair` | Recover data from truncated/corrupted files |
+| `bcsvCompare` | Compare two files (with float tolerance) |
+| `bcsvGenerator` | Generate synthetic test datasets |
+
+```bash
+csv2bcsv data.csv data.bcsv        # from an activated environment
+```
+
+```python
+import pybcsv
+
+pybcsv.tools.run("csv2bcsv", "data.csv", "data.bcsv", "--overwrite")
+print(pybcsv.tools.run("bcsvHeader", "data.bcsv").stdout)
+pybcsv.tools.path("csv2bcsv")      # absolute path, e.g. for custom pipelines
+```
+
+Source builds can opt out with `-DPYBCSV_BUILD_TOOLS=OFF`; the full tool suite
+(and docs) live in the main repository under `src/tools/`.
+
 ## Parquet Conversion Tools (CLI)
 
 Installing `pybcsv` provides two streaming command-line converters (require the

pybcsv-1.5.12/VERSION.txt

@@ -0,0 +1 @@
+1.5.11