selectolax 0.3.31__tar.gz → 0.3.33__tar.gz

{selectolax-0.3.31 → selectolax-0.3.33}/CHANGES.rst

@@ -1,6 +1,20 @@
 selectolax Changelog
 ====================
 
+Version 0.3.33
+-------------
+Released
+
+- Add `merge_text_nodes` to lexbor backend. Fixes #170. @amirshukayev
+- Performance improvements in Cython code. @Vizonex
+
+Version 0.3.32
+-------------
+
+Released
+
+- Update lexbor. New version of lexbor fixes bugs with CSS selectors.
+
 Version 0.3.31
 -------------
 

{selectolax-0.3.31/selectolax.egg-info → selectolax-0.3.33}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: selectolax
-Version: 0.3.31
+Version: 0.3.33
 Summary: Fast HTML5 parser with CSS selectors.
 Home-page: https://github.com/rushter/selectolax
 Author: Artem Golubin
@@ -167,12 +167,12 @@ selectolax (Lexbor)           2.39 sec.
 Links
 -----
 
-*  `selectolax API reference <http://selectolax.readthedocs.io/en/latest/parser.html>`_
+*  `selectolax API reference <https://selectolax.readthedocs.io/en/latest/index.html>`_
 *  `Video introduction to web scraping using selectolax <https://youtu.be/HpRsfpPuUzE>`_
 *  `How to Scrape 7k Products with Python using selectolax and httpx <https://www.youtube.com/watch?v=XpGvq755J2U>`_
 *  `Detailed overview <https://github.com/rushter/selectolax/blob/master/examples/walkthrough.ipynb>`_
 *  `Modest introduction <https://lexborisov.github.io/Modest/>`_
-*  `Modest benchmark <http://lexborisov.github.io/benchmark-html-persers/>`_
+*  `Modest benchmark <https://lexborisov.github.io/benchmark-html-parsers/>`_
 *  `Python benchmark <https://rushter.com/blog/python-fast-html-parser/>`_
 *  `Another Python benchmark <https://www.peterbe.com/plog/selectolax-or-pyquery>`_
 

{selectolax-0.3.31 → selectolax-0.3.33}/README.rst

@@ -138,12 +138,12 @@ selectolax (Lexbor)           2.39 sec.
 Links
 -----
 
-*  `selectolax API reference <http://selectolax.readthedocs.io/en/latest/parser.html>`_
+*  `selectolax API reference <https://selectolax.readthedocs.io/en/latest/index.html>`_
 *  `Video introduction to web scraping using selectolax <https://youtu.be/HpRsfpPuUzE>`_
 *  `How to Scrape 7k Products with Python using selectolax and httpx <https://www.youtube.com/watch?v=XpGvq755J2U>`_
 *  `Detailed overview <https://github.com/rushter/selectolax/blob/master/examples/walkthrough.ipynb>`_
 *  `Modest introduction <https://lexborisov.github.io/Modest/>`_
-*  `Modest benchmark <http://lexborisov.github.io/benchmark-html-persers/>`_
+*  `Modest benchmark <https://lexborisov.github.io/benchmark-html-parsers/>`_
 *  `Python benchmark <https://rushter.com/blog/python-fast-html-parser/>`_
 *  `Another Python benchmark <https://www.peterbe.com/plog/selectolax-or-pyquery>`_
 

{selectolax-0.3.31 → selectolax-0.3.33}/lexbor/CMakeLists.txt

@@ -14,6 +14,7 @@ cmake_minimum_required(VERSION 2.8.12...3.27)
 #    LEXBOR_BUILD_TESTS                  default: OFF; Build tests
 #    LEXBOR_BUILD_TESTS_CPP              default: OFF; Build C++ tests.
 #                                         Used with LEXBOR_BUILD_TESTS
+#    LEXBOR_BUILD_BENCHMARKS             default: OFF; Build benchmarks.
 #    LEXBOR_BUILD_UTILS                  default: OFF; Build utils/helpers for project.
 #    LEXBOR_BUILD_WITH_ASAN              default: OFF; Build with address sanitizer if possible
 #    LEXBOR_BUILD_WITH_FUZZER            default: OFF; Build with fuzzer tests if possible
@@ -50,6 +51,7 @@ option(LEXBOR_BUILD_EXAMPLES "Build examples" OFF)
 option(LEXBOR_BUILD_TESTS "Build tests" OFF)
 option(LEXBOR_BUILD_TESTS_CPP "Build C++ tests" OFF)
 option(LEXBOR_BUILD_UTILS "Build utils" OFF)
+option(LEXBOR_BUILD_BENCHMARKS "Build with benchmarks" OFF)
 option(LEXBOR_BUILD_WITH_ASAN "Build with address sanitizer" OFF)
 option(LEXBOR_BUILD_WITH_FUZZER "Build with fuzzer" OFF)
 option(LEXBOR_INSTALL_HEADERS "Install header files" ON)
@@ -67,6 +69,11 @@ IF(LEXBOR_BUILD_TESTS_CPP)
     enable_language(CXX)
 ENDIF()
 
+IF(LEXBOR_BUILD_BENCHMARKS)
+    add_definitions(-DLEXBOR_WITH_PERF)
+    message(STATUS "Build with LEXBOR_BUILD_BENCHMARKS=ON, hard set LEXBOR_WITH_PERF as defined.")
+ENDIF()
+
 ################
 ## Version and path
 #########################
@@ -326,6 +333,13 @@ IF(LEXBOR_BUILD_UTILS)
     add_subdirectory(utils)
 ENDIF()
 
+################
+## Benchmarks
+#########################
+IF(LEXBOR_BUILD_BENCHMARKS)
+    add_subdirectory(benchmarks)
+ENDIF()
+
 ################
 ## Build an RPM.
 #########################

{selectolax-0.3.31 → selectolax-0.3.33}/lexbor/source/lexbor/core/in.c

@@ -65,7 +65,7 @@ lexbor_in_node_make(lexbor_in_t *incoming, lexbor_in_node_t *last_node,
 
     node->opt = LEXBOR_IN_OPT_UNDEF;
     node->begin = buf;
-    node->end = buf + buf_size;
+    node->end = buf ? (buf + buf_size) : NULL;
     node->use = buf;
 
     if (last_node != NULL) {

{selectolax-0.3.31 → selectolax-0.3.33}/lexbor/source/lexbor/core/str.c

@@ -133,6 +133,10 @@ lexbor_str_append(lexbor_str_t *str, lexbor_mraw_t *mraw,
 {
     lxb_char_t *data_begin;
 
+    if (length == 0) {
+        return str->data;
+    }
+
     lexbor_str_check_size_arg_m(str, lexbor_str_size(str),
                                 mraw, (length + 1), NULL);
 

{selectolax-0.3.31 → selectolax-0.3.33}/lexbor/source/lexbor/dom/interfaces/node.c

@@ -248,11 +248,6 @@ lxb_dom_node_t *
 lxb_dom_node_destroy(lxb_dom_node_t *node)
 {
     lxb_dom_node_remove(node);
-
-    if (node->owner_document->node_cb->destroy != NULL) {
-        node->owner_document->node_cb->destroy(node);
-    }
-
     return lxb_dom_document_destroy_interface(node);
 }