@pulsar-edit/fuzzy-native 1.2.4

package/src/binding.cpp

@@ -0,0 +1,233 @@
+#include <nan.h>
+#include <vector>
+#include <unordered_map>
+#include <chrono>
+
+#include "MatcherBase.h"
+
+using namespace Nan;
+
+#define CHECK(cond, msg) \
+  if (!(cond))           \
+  {                      \
+    ThrowTypeError(msg); \
+    return;              \
+  }
+
+template <typename T>
+T get_property(const v8::Local<v8::Object> &object, const char *name)
+{
+  auto prop = Nan::Get(object, Nan::New(name).ToLocalChecked());
+  if (prop.IsEmpty())
+  {
+    return T();
+  }
+  Nan::Maybe<T> result = Nan::To<T>(prop.ToLocalChecked());
+  if (result.IsNothing())
+  {
+    return T();
+  }
+  return result.FromJust();
+}
+
+/**
+ * This saves one string copy over using v8::String::Utf8Value.
+ */
+std::string to_std_string(const v8::Local<v8::String> &v8str)
+{
+  v8::Isolate *isolate = v8::Isolate::GetCurrent();
+  std::string str(v8str->Utf8Length(isolate), ' ');
+  v8str->WriteUtf8(isolate, &str[0]);
+  return str;
+}
+
+std::string get_string_property(const v8::Local<v8::Object> &object,
+                                const char *name)
+{
+  auto prop =
+      Nan::Get(object, Nan::New(name).ToLocalChecked());
+  if (!prop.IsEmpty())
+  {
+    auto propLocal = prop.ToLocalChecked();
+    if (propLocal->IsNull() || propLocal->IsUndefined())
+    {
+      return std::string("");
+    }
+    if (!propLocal->IsString())
+    {
+      std::string msg =
+          std::string("property ") +
+          name +
+          std::string(" must be a string");
+      ThrowTypeError(msg.c_str());
+    }
+
+    return to_std_string(Nan::To<v8::String>(propLocal).ToLocalChecked());
+  }
+  return std::string("");
+}
+
+Persistent<v8::Function> MatcherConstructor;
+
+class Matcher : public ObjectWrap
+{
+public:
+  static void Init(v8::Local<v8::Object> exports)
+  {
+    // Prepare constructor template
+    v8::Local<v8::FunctionTemplate> tpl =
+        New<v8::FunctionTemplate>(Matcher::Create);
+    tpl->SetClassName(New("Matcher").ToLocalChecked());
+    tpl->InstanceTemplate()->SetInternalFieldCount(1);
+
+    // Prototype
+    SetPrototypeMethod(tpl, "match", Match);
+    SetPrototypeMethod(tpl, "addCandidates", AddCandidates);
+    SetPrototypeMethod(tpl, "removeCandidates", RemoveCandidates);
+    SetPrototypeMethod(tpl, "setCandidates", SetCandidates);
+
+    v8::Local<v8::Context> context = Nan::GetCurrentContext();
+
+    MatcherConstructor.Reset(tpl->GetFunction(context).ToLocalChecked());
+    Set(exports, Nan::New("Matcher").ToLocalChecked(), tpl->GetFunction(context).ToLocalChecked());
+  }
+
+  static void Create(const Nan::FunctionCallbackInfo<v8::Value> &info)
+  {
+    CHECK(info.IsConstructCall(), "Use 'new' to construct Matcher");
+    auto obj = new Matcher();
+    obj->Wrap(info.This());
+    AddCandidates(info);
+    info.GetReturnValue().Set(info.This());
+  }
+
+  static void Match(const FunctionCallbackInfo<v8::Value> &info)
+  {
+    if (info.Length() < 1)
+    {
+      Nan::ThrowTypeError("Wrong number of arguments");
+      return;
+    }
+
+    CHECK(info[0]->IsString(), "First argument should be a query string");
+    std::string query(to_std_string(Nan::To<v8::String>(info[0]).ToLocalChecked()));
+
+    MatcherOptions options;
+    if (info.Length() > 1)
+    {
+      CHECK(info[1]->IsObject(), "Second argument should be an options object");
+      auto options_obj = Nan::To<v8::Object>(info[1]).ToLocalChecked();
+      options.case_sensitive = get_property<bool>(options_obj, "caseSensitive");
+      options.smart_case = get_property<bool>(options_obj, "smartCase");
+      options.num_threads = get_property<int>(options_obj, "numThreads");
+      options.max_results = get_property<int>(options_obj, "maxResults");
+      options.max_gap = get_property<int>(options_obj, "maxGap");
+      options.record_match_indexes =
+          get_property<bool>(options_obj, "recordMatchIndexes");
+      options.fuzzaldrin =
+          get_string_property(options_obj, "algorithm") == "fuzzaldrin";
+      options.root_path = get_string_property(options_obj, "rootPath");
+    }
+
+    auto idKey = New("id").ToLocalChecked();
+    auto valueKey = New("value").ToLocalChecked();
+    auto scoreKey = New("score").ToLocalChecked();
+    auto matchIndexesKey = New("matchIndexes").ToLocalChecked();
+
+    auto matcher = Unwrap<Matcher>(info.This());
+    std::vector<MatchResult> matches =
+        matcher->impl_.findMatches(query, options);
+    auto result = New<v8::Array>();
+    size_t result_count = 0;
+    for (const auto &match : matches)
+    {
+      auto obj = New<v8::Object>();
+      Set(obj, idKey, New<v8::Uint32>(match.id));
+      Set(obj, scoreKey, New(match.score));
+      Set(obj, valueKey, New(*match.value).ToLocalChecked());
+
+      v8::Local<v8::Context> context = Nan::GetCurrentContext();
+      if (match.matchIndexes != nullptr)
+      {
+        auto array = New<v8::Array>(match.matchIndexes->size());
+        for (size_t i = 0; i < array->Length(); i++)
+        {
+          array->Set(context, i, New(match.matchIndexes->at(i)));
+        }
+        Set(obj, matchIndexesKey, array);
+      }
+      result->Set(context, result_count++, obj);
+    }
+    info.GetReturnValue().Set(result);
+  }
+
+  static void AddCandidates(const FunctionCallbackInfo<v8::Value> &info)
+  {
+    auto matcher = Unwrap<Matcher>(info.This());
+    if (info.Length() > 0)
+    {
+      CHECK(info[0]->IsArray(), "Expected an array of unsigned 32-bit integer ids as the first argument");
+      CHECK(info[1]->IsArray(), "Expected an array of strings as the second argument");
+
+      auto ids = v8::Local<v8::Array>::Cast(info[0]);
+      auto values = v8::Local<v8::Array>::Cast(info[1]);
+
+      CHECK(ids->Length() == values->Length(), "Expected ids array and values array to have the same length");
+
+      // Create a random permutation so that candidates are shuffled.
+      std::vector<size_t> indexes(ids->Length());
+      for (size_t i = 0; i < indexes.size(); i++)
+      {
+        indexes[i] = i;
+        if (i > 0)
+        {
+          std::swap(indexes[rand() % i], indexes[i]);
+        }
+      }
+      matcher->impl_.reserve(matcher->impl_.size() + ids->Length());
+
+      v8::Local<v8::Context> context = Nan::GetCurrentContext();
+      for (auto i : indexes)
+      {
+        auto id_value = ids->Get(context, i).ToLocalChecked();
+        CHECK(id_value->IsUint32(), "Expected first array to only contain unsigned 32-bit integer ids");
+        auto id = v8::Local<v8::Uint32>::Cast(id_value)->Value();
+        auto value = to_std_string(Nan::To<v8::String>(values->Get(context, i).ToLocalChecked()).ToLocalChecked());
+        matcher->impl_.addCandidate(id, value);
+      }
+    }
+  }
+
+  static void RemoveCandidates(const FunctionCallbackInfo<v8::Value> &info)
+  {
+    auto matcher = Unwrap<Matcher>(info.This());
+    if (info.Length() > 0)
+    {
+      CHECK(info[0]->IsArray(), "Expected an array of unsigned 32-bit integer ids");
+      auto ids = v8::Local<v8::Array>::Cast(info[0]);
+
+      v8::Local<v8::Context> context = Nan::GetCurrentContext();
+      for (size_t i = 0; i < ids->Length(); i++)
+      {
+        auto id_value = ids->Get(context, i).ToLocalChecked();
+        CHECK(id_value->IsUint32(), "Expected array to only contain unsigned 32-bit integer ids");
+        auto id = v8::Local<v8::Uint32>::Cast(id_value)->Value();
+        matcher->impl_.removeCandidate(id);
+      }
+    }
+  }
+
+  static void SetCandidates(const FunctionCallbackInfo<v8::Value> &info)
+  {
+    auto matcher = Unwrap<Matcher>(info.This());
+    matcher->impl_.clear();
+    AddCandidates(info);
+  }
+
+private:
+  MatcherBase impl_;
+};
+
+void Init(v8::Local<v8::Object> exports) { Matcher::Init(exports); }
+
+NAN_MODULE_WORKER_ENABLED(addon, Init)

package/src/fuzzaldrin_score.cpp

@@ -0,0 +1,112 @@
+// Original ported from: string_score.js: String Scoring Algorithm 0.1.10
+// https://github.com/joshaven/string_score
+//
+// Copyright (C) 2009-2011 Joshaven Potter <yourtech@gmail.com>
+// Special thanks to all of the contributors listed here https://github.com/joshaven/string_score
+// MIT license: http://www.opensource.org/licenses/mit-license.php
+//
+// Re-ported from Atom's Fuzzaldrin score.js file to C++
+
+#include "fuzzaldrin_score.h"
+
+const std::string PathSeparator = "/"; // Assuming Unix-like path separator
+
+float fuzzaldrin_basename_score(const std::string& string, const std::string& query, float score) {
+  long index = string.length() - 1;
+  while (string[index] == PathSeparator[0]) { index--; } // Skip trailing slashes
+  std::size_t slashCount = 0;
+  const std::size_t lastCharacter = index;
+  std::string base;
+
+  while (index >= 0) {
+    if (string[index] == PathSeparator[0]) {
+      slashCount++;
+      if (base.empty()) {
+        base = string.substr(index + 1, lastCharacter - index);
+      }
+    } else if (index == 0) {
+      if (lastCharacter < (string.length() - 1)) {
+        if (base.empty()) {
+          base = string.substr(0, lastCharacter + 1);
+        }
+      } else {
+        if (base.empty()) {
+          base = string;
+        }
+      }
+    }
+    index--;
+  }
+
+  // Basename matches count for more.
+  if (base == string) {
+      score *= 2;
+  } else if (!base.empty()) {
+      score += fuzzaldrin_score(base, query);
+  }
+
+  // Shallow files are scored higher
+  const std::size_t segmentCount = slashCount + 1;
+  const std::size_t depth = std::max<std::size_t>(1, 10 - segmentCount);
+  score *= depth * 0.01;
+  return score;
+}
+
+bool queryIsLastPathSegment(const std::string& string, const std::string& query) {
+    auto res = string[string.length() - query.length() - 1] == PathSeparator[0];
+
+    if (string[string.length() - query.length() - 1] == PathSeparator[0]) {
+      auto res2 = string.rfind(query) == (string.length() - query.length());
+      return string.rfind(query) == (string.length() - query.length());
+    }
+    return false;
+}
+
+float fuzzaldrin_score(const std::string& candidate, const std::string& query) {
+    std::string string = candidate;
+
+    if (string == query) {
+      return 1.0;
+    }
+    if (queryIsLastPathSegment(string, query)) {
+      return 1.0;
+    }
+
+    float totalCharacterScore = 0.0;
+    const std::size_t queryLength = query.length();
+    const std::size_t stringLength = string.length();
+
+    std::size_t indexInQuery = 0;
+    std::size_t indexInString = 0;
+
+    while (indexInQuery < queryLength) {
+        char character = query[indexInQuery++];
+        std::size_t lowerCaseIndex = string.find(std::tolower(character));
+        std::size_t upperCaseIndex = string.find(std::toupper(character));
+        std::size_t minIndex = std::min(lowerCaseIndex, upperCaseIndex);
+        if (minIndex == std::string::npos) { minIndex = std::max(lowerCaseIndex, upperCaseIndex); }
+        indexInString = minIndex;
+        if (indexInString == std::string::npos) { return 0.0; }
+
+        float characterScore = 0.1;
+
+        // Same case bonus.
+        if (string[indexInString] == character) { characterScore += 0.1; }
+
+        if ((indexInString == 0) || (string[indexInString - 1] == PathSeparator[0])) {
+            // Start of string bonus
+            characterScore += 0.8;
+        } else if (string[indexInString - 1] == '-' || string[indexInString - 1] == '_' || string[indexInString - 1] == ' ') {
+            // Start of word bonus
+            characterScore += 0.7;
+        }
+
+        // Trim string to after the current abbreviation match
+        string = string.substr(indexInString + 1);
+        totalCharacterScore += characterScore;
+    }
+
+    const float queryScore = totalCharacterScore / queryLength;
+    auto div = (queryLength / (float) stringLength);
+    return ((queryScore * (queryLength / (float) stringLength)) + queryScore) / 2.0;
+}

package/src/fuzzaldrin_score.h

@@ -0,0 +1,5 @@
+#pragma once
+#include <string>
+
+float fuzzaldrin_score(const std::string& string, const std::string& query);
+float fuzzaldrin_basename_score(const std::string& string, const std::string& query, float score);

package/src/memrchr.h

@@ -0,0 +1,179 @@
+/* memrchr -- find the last occurrence of a byte in a memory block
+   Copyright (C) 1991, 93, 96, 97, 99, 2000, 2012 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
+   with help from Dan Sahlin (dan@sics.se) and
+   commentary by Jim Blandy (jimb@ai.mit.edu);
+   adaptation to memchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
+   and implemented by Roland McGrath (roland@ai.mit.edu).
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <stdlib.h>
+
+#ifdef HAVE_CONFIG_H
+# include <config.h>
+#endif
+
+#undef __ptr_t
+#define __ptr_t void *
+
+#if defined _LIBC
+# include <string.h>
+# include <memcopy.h>
+#endif
+
+#if defined HAVE_LIMITS_H || defined _LIBC
+# include <limits.h>
+#endif
+
+#define LONG_MAX_32_BITS 2147483647
+
+#ifndef LONG_MAX
+# define LONG_MAX LONG_MAX_32_BITS
+#endif
+
+#include <sys/types.h>
+
+/* Search no more than N bytes of S for C.  */
+inline __ptr_t memrchr(const __ptr_t s, int c_in, size_t n)
+{
+  const unsigned char *char_ptr;
+  const unsigned long int *longword_ptr;
+  unsigned long int longword, magic_bits, charmask;
+  unsigned char c;
+
+  c = (unsigned char) c_in;
+
+  /* Handle the last few characters by reading one character at a time.
+     Do this until CHAR_PTR is aligned on a longword boundary.  */
+  for (char_ptr = (const unsigned char *) s + n;
+       n > 0 && ((unsigned long int) char_ptr
+		 & (sizeof (longword) - 1)) != 0;
+       --n)
+    if (*--char_ptr == c)
+      return (__ptr_t) char_ptr;
+
+  /* All these elucidatory comments refer to 4-byte longwords,
+     but the theory applies equally well to 8-byte longwords.  */
+
+  longword_ptr = (const unsigned long int *) char_ptr;
+
+  /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
+     the "holes."  Note that there is a hole just to the left of
+     each byte, with an extra at the end:
+     bits:  01111110 11111110 11111110 11111111
+     bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD
+     The 1-bits make sure that carries propagate to the next 0-bit.
+     The 0-bits provide holes for carries to fall into.  */
+
+  if (sizeof (longword) != 4 && sizeof (longword) != 8)
+    abort ();
+
+#if LONG_MAX <= LONG_MAX_32_BITS
+  magic_bits = 0x7efefeff;
+#else
+  magic_bits = ((unsigned long int) 0x7efefefe << 32) | 0xfefefeff;
+#endif
+
+  /* Set up a longword, each of whose bytes is C.  */
+  charmask = c | (c << 8);
+  charmask |= charmask << 16;
+#if LONG_MAX > LONG_MAX_32_BITS
+  charmask |= charmask << 32;
+#endif
+
+  /* Instead of the traditional loop which tests each character,
+     we will test a longword at a time.  The tricky part is testing
+     if *any of the four* bytes in the longword in question are zero.  */
+  while (n >= sizeof (longword))
+    {
+      /* We tentatively exit the loop if adding MAGIC_BITS to
+	 LONGWORD fails to change any of the hole bits of LONGWORD.
+	 1) Is this safe?  Will it catch all the zero bytes?
+	 Suppose there is a byte with all zeros.  Any carry bits
+	 propagating from its left will fall into the hole at its
+	 least significant bit and stop.  Since there will be no
+	 carry from its most significant bit, the LSB of the
+	 byte to the left will be unchanged, and the zero will be
+	 detected.
+	 2) Is this worthwhile?  Will it ignore everything except
+	 zero bytes?  Suppose every byte of LONGWORD has a bit set
+	 somewhere.  There will be a carry into bit 8.  If bit 8
+	 is set, this will carry into bit 16.  If bit 8 is clear,
+	 one of bits 9-15 must be set, so there will be a carry
+	 into bit 16.  Similarly, there will be a carry into bit
+	 24.  If one of bits 24-30 is set, there will be a carry
+	 into bit 31, so all of the hole bits will be changed.
+	 The one misfire occurs when bits 24-30 are clear and bit
+	 31 is set; in this case, the hole at bit 31 is not
+	 changed.  If we had access to the processor carry flag,
+	 we could close this loophole by putting the fourth hole
+	 at bit 32!
+	 So it ignores everything except 128's, when they're aligned
+	 properly.
+	 3) But wait!  Aren't we looking for C, not zero?
+	 Good point.  So what we do is XOR LONGWORD with a longword,
+	 each of whose bytes is C.  This turns each byte that is C
+	 into a zero.  */
+
+      longword = *--longword_ptr ^ charmask;
+
+      /* Add MAGIC_BITS to LONGWORD.  */
+      if ((((longword + magic_bits)
+
+	    /* Set those bits that were unchanged by the addition.  */
+	    ^ ~longword)
+
+	   /* Look at only the hole bits.  If any of the hole bits
+	      are unchanged, most likely one of the bytes was a
+	      zero.  */
+	   & ~magic_bits) != 0)
+	{
+	  /* Which of the bytes was C?  If none of them were, it was
+	     a misfire; continue the search.  */
+
+	  const unsigned char *cp = (const unsigned char *) longword_ptr;
+
+#if LONG_MAX > 2147483647
+	  if (cp[7] == c)
+	    return (__ptr_t) &cp[7];
+	  if (cp[6] == c)
+	    return (__ptr_t) &cp[6];
+	  if (cp[5] == c)
+	    return (__ptr_t) &cp[5];
+	  if (cp[4] == c)
+	    return (__ptr_t) &cp[4];
+#endif
+	  if (cp[3] == c)
+	    return (__ptr_t) &cp[3];
+	  if (cp[2] == c)
+	    return (__ptr_t) &cp[2];
+	  if (cp[1] == c)
+	    return (__ptr_t) &cp[1];
+	  if (cp[0] == c)
+	    return (__ptr_t) cp;
+	}
+
+      n -= sizeof (longword);
+    }
+
+  char_ptr = (const unsigned char *) longword_ptr;
+
+  while (n-- > 0)
+    {
+      if (*--char_ptr == c)
+	return (__ptr_t) char_ptr;
+    }
+
+  return 0;
+}