Spelling

CHANGELOG.md

@@ -47,7 +47,7 @@ This is a list of notable changes to Hyperscan, in reverse chronological order.
 - Bugfix for issue #239: fix hyperscan compile issue under gcc-10.
 - Add VLAN packets processing capability in pcap analysis script. (#214)
 - Avoid extra convert instruction for "Noodle". (#221)
-- Add Hyperscan version marcro in `hs.h`. (#222)
+- Add Hyperscan version macro in `hs.h`. (#222)
 
 ## [5.2.1] 2019-10-13
 - Bugfix for issue #186: fix compile issue when `BUILD_SHARED_LIBS` is on in
@@ -57,7 +57,7 @@ This is a list of notable changes to Hyperscan, in reverse chronological order.
 ## [5.2.0] 2019-07-12
 - Literal API: add new API `hs_compile_lit()` and `hs_compile_lit_multi()` to
   process pure literal rule sets. The 2 literal APIs treat each expression text
-  in a literal sense without recognizing any regular grammers.
+  in a literal sense without recognizing any regular grammars.
 - Logical combination: add support for purely negative combinations, which
   report match at EOD in case of no sub-expressions matched.
 - Windows porting: support shared library (DLL) on Windows with available tools
@@ -71,7 +71,7 @@ This is a list of notable changes to Hyperscan, in reverse chronological order.
 
 ## [5.1.1] 2019-04-03
 - Add extra detection and handling when invalid rose programs are triggered.
-- Bugfix for issue #136: fix CMake parsing of CPU architecure for GCC-9.
+- Bugfix for issue #136: fix CMake parsing of CPU architecture for GCC-9.
 - Bugfix for issue #137: avoid file path impact on fat runtime build.
 - Bugfix for issue #141: fix rose literal programs for multi-pattern
   matching when no pattern ids are provided.
@@ -330,7 +330,7 @@ This is a list of notable changes to Hyperscan, in reverse chronological order.
   line with the behaviour of `hs_close_stream()`.
 - Disallow bounded repeats with a very large minimum repeat but no maximum,
   i.e. {N,} for very large N.
-- Reduce compile memory usage in literal set explansion for some large cases.
+- Reduce compile memory usage in literal set expansion for some large cases.
 
 ## [4.0.0] 2015-10-20
 - Original release of Hyperscan as open-source software.

README.md

@@ -22,7 +22,7 @@ project repository.
 
 # Versioning
 
-The `master` branch on Github will always contain the most recent release of
+The `master` branch on GitHub will always contain the most recent release of
 Hyperscan. Each version released to `master` goes through QA and testing before
 it is released; if you're a user, rather than a developer, this is the version
 you should be using.
@@ -36,7 +36,7 @@ The official homepage for Hyperscan is at [www.hyperscan.io](https://www.hypersc
 
 If you have questions or comments, we encourage you to [join the mailing
 list](https://lists.01.org/mailman/listinfo/hyperscan). Bugs can be filed by
-sending email to the list, or by creating an issue on Github.
+sending email to the list, or by creating an issue on GitHub.
 
 If you wish to contact the Hyperscan team at Intel directly, without posting
 publicly to the mailing list, send email to

chimera/ch_common.h

@@ -129,7 +129,7 @@ ch_error_t HS_CDECL ch_database_info(const ch_database_t *database,
  * more memory at runtime as required.
  *
  * If Chimera is to be used in a multi-threaded, or similarly concurrent
- * environment, the allocation function will need to be re-entrant, or
+ * environment, the allocation function will need to be reentrant, or
  * similarly safe for concurrent use.
  *
  * @param size

doc/dev-reference/chimera.rst

@@ -204,7 +204,7 @@ databases, only a single scratch region is necessary: in this case, calling
 will ensure that the scratch space is large enough to support scanning against
 any of the given databases.
 
-While the Chimera library is re-entrant, the use of scratch spaces is not.
+While the Chimera library is reentrant, the use of scratch spaces is not.
 For example, if by design it is deemed necessary to run recursive or nested
 scanning (say, from the match callback function), then an additional scratch
 space is required for that context.

doc/dev-reference/hyperscan.doxyfile.in

@@ -268,7 +268,7 @@ OPTIMIZE_OUTPUT_VHDL   = NO
 # parses. With this tag you can assign which parser to use for a given
 # extension. Doxygen has a built-in mapping, but you can override or extend it
 # using this tag. The format is ext=language, where ext is a file extension, and
-# language is one of the parsers supported by doxygen: IDL, Java, Javascript,
+# language is one of the parsers supported by doxygen: IDL, Java, JavaScript,
 # C#, C, C++, D, PHP, Objective-C, Python, Fortran (fixed format Fortran:
 # FortranFixed, free formatted Fortran: FortranFree, unknown formatted Fortran:
 # Fortran. In the later case the parser tries to guess whether the code is fixed
@@ -659,7 +659,7 @@ SHOW_NAMESPACES        = YES
 # The FILE_VERSION_FILTER tag can be used to specify a program or script that
 # doxygen should invoke to get the current version for each file (typically from
 # the version control system). Doxygen will invoke the program by executing (via
-# popen()) the command command input-file, where command is the value of the
+# popen()) the command input-file, where command is the value of the
 # FILE_VERSION_FILTER tag, and input-file is the name of an input file provided
 # by doxygen. Whatever the program writes to standard output is used as the file
 # version. For an example see the documentation.
@@ -1424,7 +1424,7 @@ EXT_LINKS_IN_WINDOW    = NO
 
 FORMULA_FONTSIZE       = 10
 
-# Use the FORMULA_TRANPARENT tag to determine whether or not the images
+# Use the FORMULA_TRANSPARENT tag to determine whether or not the images
 # generated for formulas are transparent PNGs. Transparent PNGs are not
 # supported properly for IE 6.0, but are supported on all modern browsers.
 #
@@ -1436,7 +1436,7 @@ FORMULA_FONTSIZE       = 10
 FORMULA_TRANSPARENT    = YES
 
 # Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see
-# http://www.mathjax.org) which uses client side Javascript for the rendering
+# http://www.mathjax.org) which uses client side JavaScript for the rendering
 # instead of using pre-rendered bitmaps. Use this if you do not have LaTeX
 # installed or if you want to formulas look prettier in the HTML output. When
 # enabled you may also need to install MathJax separately and configure the path
@@ -1506,7 +1506,7 @@ MATHJAX_CODEFILE       =
 SEARCHENGINE           = YES
 
 # When the SERVER_BASED_SEARCH tag is enabled the search engine will be
-# implemented using a web server instead of a web client using Javascript. There
+# implemented using a web server instead of a web client using JavaScript. There
 # are two flavors of web server based searching depending on the EXTERNAL_SEARCH
 # setting. When disabled, doxygen will generate a PHP script for searching and
 # an index file used by the script. When EXTERNAL_SEARCH is enabled the indexing

doc/dev-reference/performance.rst

@@ -316,7 +316,7 @@ see reduced performance when the single-match flag is used.
 Start of Match flag
 ********************
 
-.. tip:: Do not request Start of Match information if it is not not needed.
+.. tip:: Do not request Start of Match information if it is not needed.
 
 Start of Match (SOM) information can be expensive to gather and can require
 large amounts of stream state to store in streaming mode. As such, SOM

doc/dev-reference/runtime.rst

@@ -170,7 +170,7 @@ databases, only a single scratch region is necessary: in this case, calling
 will ensure that the scratch space is large enough to support scanning against
 any of the given databases.
 
-While the Hyperscan library is re-entrant, the use of scratch spaces is not.
+While the Hyperscan library is reentrant, the use of scratch spaces is not.
 For example, if by design it is deemed necessary to run recursive or nested
 scanning (say, from the match callback function), then an additional scratch
 space is required for that context.

src/fdr/fdr_compile.cpp

@@ -742,7 +742,7 @@ void buildSquashMask(vector<hwlmLiteral> &lits, u32 id1, u32 bucket1,
                 return;
             }
             /* if lit2 is a suffix but doesn't pass included checks for
-             * extra info, we give up sqaushing */
+             * extra info, we give up squashing */
             if (includedCheck(lit1, lit2)) {
                 DEBUG_PRINTF("find exceptional suffix %u\n", lit2.id);
                 exception_map[id1].insert(id2);

src/hs.cpp

@@ -334,7 +334,7 @@ hs_compile_lit_multi_int(const char *const *expressions, const unsigned *flags,
 
     if (!checkPlatform(platform, comp_error)) {
         *db = nullptr;
-        assert(*comp_error); // set by checkPlattform.
+        assert(*comp_error); // set by checkPlatform.
         return HS_COMPILER_ERROR;
     }
 
@@ -399,7 +399,7 @@ hs_compile_lit_multi_int(const char *const *expressions, const unsigned *flags,
         return HS_COMPILER_ERROR;
     }
     catch (...) {
-        assert(!"Internal errror, unexpected exception");
+        assert(!"Internal error, unexpected exception");
         *db = nullptr;
         *comp_error = const_cast<hs_compile_error_t *>(&hs_einternal);
         return HS_COMPILER_ERROR;

src/hs_common.h

@@ -277,7 +277,7 @@ hs_error_t HS_CDECL hs_serialized_database_info(const char *bytes,
  * allocate stream state.
  *
  * If Hyperscan is to be used in a multi-threaded, or similarly concurrent
- * environment, the allocation function will need to be re-entrant, or
+ * environment, the allocation function will need to be reentrant, or
  * similarly safe for concurrent use.
  *
  * @param size

src/hs_runtime.h

@@ -96,7 +96,7 @@ typedef struct hs_scratch hs_scratch_t;
  * @param from
  *      - If a start of match flag is enabled for the current pattern, this
  *        argument will be set to the start of match for the pattern assuming
- *        that that start of match value lies within the current 'start of match
+ *        that the start of match value lies within the current 'start of match
  *        horizon' chosen by one of the SOM_HORIZON mode flags.
 
  *      - If the start of match value lies outside this horizon (possible only

src/nfa/goughcompile.cpp

@@ -270,7 +270,7 @@ void makeCFG_edge(GoughGraph &cfg, const map<u32, u32> &som_creators,
                 u32 adjust = som_creators.at(input_slot);
 
                 if (vnew && vnew->adjust >= adjust) {
-                    DEBUG_PRINTF("skipping %u as domininated by adj%u\n",
+                    DEBUG_PRINTF("skipping %u as dominated by adj%u\n",
                                  adjust, vnew->adjust);
                     continue; /* deeper starts can be seen to statically
                                  dominate */

src/nfa/mcsheng_compile.cpp

@@ -546,7 +546,7 @@ dstate_id_t find_sheng_states(dfa_info &info,
             continue;
         }
         DEBUG_PRINTF("considering cyclic %zu\n", g[v].index);
-        /* get an estimate of stickness of the cyclic: assume any edges from
+        /* get an estimate of stickiness of the cyclic: assume any edges from
          * states with larger state ids are back edges */
         CharReach est_back_reach;
         for (const auto &u : inv_adjacent_vertices_range(v, g)) {

src/nfa/nfa_api.h

@@ -62,7 +62,7 @@ enum nfa_zombie_status {
  * to a corresponding compressed stream state (@ref mq::streamState).
  *
  * @param nfa engine the state belongs to
- * @param q queue for the engine. The final compressed stream stream is placed
+ * @param q queue for the engine. The final compressed stream is placed
  *        in the location indicated by @ref mq::streamState
  * @param loc the location corresponding to the engine's current state
  */

src/nfa/nfa_dump_api.h

@@ -43,7 +43,7 @@ namespace ue2 {
 
 /**
  * \brief Dump files representing the engine. All files dumped should begin with
- * path/prefix specified by base. Generally a text file and a grpahviz (dot)
+ * path/prefix specified by base. Generally a text file and a graphviz (dot)
  * files should be produced.
  */
 void nfaGenerateDumpFiles(const struct NFA *nfa, const std::string &base);

src/nfagraph/ng_anchored_dots.cpp

@@ -216,7 +216,7 @@ void reformAnchoredRepeatsComponent(NGHolder &g,
     }
 
     if (!otherV.empty()) {
-        /* We require that the successors of the dot node are are the same
+        /* We require that the successors of the dot node are the same
          * as the start vertex. TODO: remember why.
          */
         if (selfLoop) {

src/nfagraph/ng_depth.cpp

@@ -326,7 +326,7 @@ vector<NFAVertexRevDepth> calcRevDepths(const NGHolder &g) {
     calcAndStoreDepth<RevNFAGraph, NFAVertexRevDepth>(
         rg, g.accept, deadNodes, dMin, dMax, depths,
         &NFAVertexRevDepth::toAccept);
-    DEBUG_PRINTF("doing accepteod\n");
+    DEBUG_PRINTF("doing acceptEod\n");
     deadNodes[NODE_ACCEPT] = true; // Hide accept->acceptEod edge.
     calcAndStoreDepth<RevNFAGraph, NFAVertexRevDepth>(
         rg, g.acceptEod, deadNodes, dMin, dMax, depths,
@@ -367,7 +367,7 @@ vector<NFAVertexBidiDepth> calcBidiDepths(const NGHolder &g) {
     calcAndStoreDepth<RevNFAGraph, NFAVertexBidiDepth>(
         rg, g.accept, deadNodes, dMin, dMax, depths,
         &NFAVertexBidiDepth::toAccept);
-    DEBUG_PRINTF("doing accepteod\n");
+    DEBUG_PRINTF("doing acceptEod\n");
     deadNodes[NODE_ACCEPT] = true; // Hide accept->acceptEod edge.
     calcAndStoreDepth<RevNFAGraph, NFAVertexBidiDepth>(
         rg, g.acceptEod, deadNodes, dMin, dMax, depths,

src/nfagraph/ng_equivalence.cpp

@@ -508,7 +508,7 @@ void mergeClass(vector<unique_ptr<VertexInfo>> &infos, NGHolder &g,
 
     /* For left equivalence, if the members have different reporting behaviour
      * we sometimes require two vertices to be created (one connected to accept
-     * and one to accepteod) */
+     * and one to acceptEod) */
 
     NFAVertex old_v = (*cur_class_vertices.begin())->v;
     NFAVertex new_v = clone_vertex(g, old_v); /* set up new vertex with same

src/nfagraph/ng_literal_analysis.cpp

@@ -874,7 +874,7 @@ bool literalIsWholeGraph(const NGHolder &g, const ue2_literal &lit) {
         const CharReach &cr_l = *it;
 
         if (!cr_l.isSubsetOf(cr_g)) {
-            /* running over the prefix is needed to prevent false postives */
+            /* running over the prefix is needed to prevent false positives */
             DEBUG_PRINTF("reach fail\n");
             return false;
         }

src/nfagraph/ng_violet.cpp

@@ -1304,7 +1304,7 @@ void splitEdgesByCut(NGHolder &h, RoseInGraph &vg,
 
             vector<NFAVertex> adj;
             insert(&adj, adj.end(), adjacent_vertices(pivot, h));
-            /* we can ignore presence of accept, accepteod in adj as it is best
+            /* we can ignore presence of accept, acceptEod in adj as it is best
                effort */
 
             if (!contains(done_rhs, adj)) {
@@ -2018,7 +2018,7 @@ bool improvePrefix(NGHolder &h, RoseInGraph &vg, const vector<RoseInEdge> &ee,
         return true;
     }
 
-    /* large back edges may prevent us identifing anchored or transient cases
+    /* large back edges may prevent us identifying anchored or transient cases
      * properly - use a simple walk instead */
 
     if (doNetflowCut(h, &depths, vg, ee, true, cc.grey)) {
@@ -2218,7 +2218,7 @@ bool improveInfix(NGHolder &h, RoseInGraph &vg, const vector<RoseInEdge> &ee,
     /* look for netflow cuts which don't produce good prefixes */
     bool rv = doNetflowCut(h, nullptr, vg, ee, false, cc.grey, 8);
 
-    DEBUG_PRINTF("did netfow cut? = %d\n", (int)rv);
+    DEBUG_PRINTF("did netflow cut? = %d\n", (int)rv);
 
     return rv;
 }
@@ -2655,7 +2655,7 @@ bool lookForTrailingLiteralDotStar(const NGHolder &h,
 
 /* In streaming mode, active engines have to be caught up at stream boundaries
  * and have to be stored in stream state, so we prefer to decompose patterns
- * in to literals with no state between them if possible. */
+ * into literals with no state between them if possible. */
 static
 void decomposeLiteralChains(RoseInGraph &vg, const CompileContext &cc) {
     if (!cc.grey.violetLiteralChains) {

src/parser/Parser.rl

@@ -1549,7 +1549,7 @@ unichar readUtf8CodePoint4c(const char *s) {
               # Oniguruma - either angle braces or single quotes for this one
               ('\\g<' [^>]*? '>'|'\\g\'' [^\']*? '\'') => {
                   ostringstream str;
-                  str << "Onigiruma subroutine call at index " << ts - ptr <<
+                  str << "Oniguruma subroutine call at index " << ts - ptr <<
                          " not supported.";
                   throw ParseError(str.str());
               };

src/rose/program_runtime.c

@@ -1245,7 +1245,7 @@ int roseCheckSingleLookaround(const struct RoseEngine *t,
 }
 
 /**
- * \brief Scan around a literal, checking that that "lookaround" reach masks
+ * \brief Scan around a literal, checking that "lookaround" reach masks
  * are satisfied.
  */
 static rose_inline

src/rose/rose_build_groups.cpp

@@ -75,17 +75,17 @@ bool superStrong(const rose_literal_id &lit) {
 
 static
 bool eligibleForAlwaysOnGroup(const RoseBuildImpl &build, u32 id) {
-    auto eligble = [&](RoseVertex v) {
+    auto eligible = [&](RoseVertex v) {
         return build.isRootSuccessor(v)
         && (!build.g[v].left || !isAnchored(build.g[v].left));
     };
 
-    if (any_of_in(build.literal_info[id].vertices, eligble)) {
+    if (any_of_in(build.literal_info[id].vertices, eligible)) {
         return true;
     }
 
     for (u32 delayed_id : build.literal_info[id].delayed_ids) {
-        if (any_of_in(build.literal_info[delayed_id].vertices, eligble)) {
+        if (any_of_in(build.literal_info[delayed_id].vertices, eligible)) {
             return true;
         }
     }

src/rose/rose_build_merge.cpp

@@ -531,7 +531,7 @@ bool checkPrefix(const rose_literal_id &ul, const u32 ulag,
     }
 
     size_t min_allowed_delta = vlag - ulag;
-    DEBUG_PRINTF("min allow distace %zu\n", min_allowed_delta);
+    DEBUG_PRINTF("min allow distance %zu\n", min_allowed_delta);
 
     for (size_t i = 0; i < min_allowed_delta; i++) {
         if (stringsCanFinishAtSameSpot(ul.s, vl.s.begin(), vl.s.end() - i)) {

src/rose/rose_build_program.cpp

@@ -1646,7 +1646,7 @@ RoseProgram makeLitInitialProgram(const RoseBuildImpl &build,
                                  prog_build.floatingMinLiteralMatchOffset,
                                  program);
 
-    /* Check if we are able to deliever matches from the anchored table now */
+    /* Check if we are able to deliver matches from the anchored table now */
     if (!is_anchored_replay_program) {
         makeAnchoredLiteralDelay(build, prog_build, lit_id, program);
     }

src/rose/rose_program.h

@@ -307,7 +307,7 @@ struct ROSE_STRUCT_CHECK_BYTE {
     u32 fail_jump; //!< Jump forward this many bytes on failure.
 };
 
-// Since m128 and m256 could be missaligned in the bytecode,
+// Since m128 and m256 could be misaligned in the bytecode,
 // we'll use u8[16] and u8[32] instead in all rose_check_shufti structures.
 struct ROSE_STRUCT_CHECK_SHUFTI_16x8 {
     u8 code; //!< From enum RoseInstructionCode.

src/util/charreach_util.h

@@ -45,7 +45,7 @@ void make_caseless(CharReach *cr);
 void fill_bitvector(const CharReach &cr, u8 *bits);
 
 /**
- * \brief Generate and and compare masks for checking the char reach.
+ * \brief Generate and compare masks for checking the char reach.
  *
  * Any character c in cr will be result in (c & and_mask) == cmp_mask being true.
  * Note: characters not in cr may also pass the and/cmp checks.

src/util/logical.h

@@ -69,7 +69,7 @@ struct CombInfo {
     u64a max_offset;
 };
 
-/** Temporarily use to seperate operations' id from reports' lkey
+/** Temporarily use to separate operations' id from reports' lkey
   * when building logicalTree in shunting yard algorithm,
   * operations' id will be finally renumbered following reports' lkey. */
 #define LOGICAL_OP_BIT 0x80000000UL

src/util/multibit_compress.h

@@ -200,5 +200,5 @@ char mmbit_decompress(u8 *bits, u32 total_bits, const u8 *comp,
 } // extern "C"
 #endif
 
-#endif // MULTBIT_COMPRESS_H
+#endif // MULTIBIT_COMPRESS_H