Merge pull request #29 from quantumlib/main

latest changes

Author: noajshu

.github/workflows/prerelease.yml

@@ -32,10 +32,8 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        os: [ubuntu-24.04, macos-13]
+        os: [ubuntu-22.04, ubuntu-24.04, macos-13, macos-14]
         python-version: ['3.10', '3.11', '3.12']
-
-
     steps:
     - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
     - name: Set up Python
@@ -66,7 +64,11 @@ jobs:
       env:
         TARGET_PYTHON: ${{ matrix.python-version }}
       run: |
-        bazel build --define TARGET_VERSION="$(python -c "print(\"py${TARGET_PYTHON}\".replace(\".\", \"\"))")" --define VERSION="$(cat version/version.txt)"  :tesseract_decoder_wheel
+        glibc_version=$(ldd --version | awk '/ldd/{print $NF}')
+        export GLIBC_VERSION="${glibc_version//./_}"
+        echo $GLIBC_VERSION
+        sed "s/^MANYLINUX_VERSION.*/MANYLINUX_VERSION=\"manylinux_${GLIBC_VERSION}_x86_64.manylinux2014_x86_64\"/" BUILD -i || true
+        bazel build --define GLIBC_VERSION=$GLIBC_VERSION --define TARGET_VERSION="$(python -c "print(\"py${TARGET_PYTHON}\".replace(\".\", \"\"))")" --define VERSION="$(cat version/version.txt)"  :tesseract_decoder_wheel
 
     - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4
       with:

.github/workflows/stable-release-workflow.yml

@@ -31,7 +31,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        os: [ubuntu-24.04, macos-13]
+        os: [ubuntu-22.04, ubuntu-24.04, macos-13, macos-14]
         python-version: ['3.10', '3.11', '3.12']
 
     steps:
@@ -64,6 +64,10 @@ jobs:
       env:
         TARGET_PYTHON: ${{ matrix.python-version }}
       run: |
+        glibc_version=$(ldd --version | awk '/ldd/{print $NF}')
+        export GLIBC_VERSION="${glibc_version//./_}"
+        echo $GLIBC_VERSION
+        sed "s/^MANYLINUX_VERSION.*/MANYLINUX_VERSION=\"manylinux_${GLIBC_VERSION}_x86_64.manylinux2014_x86_64\"/" BUILD -i || true
         bazel build --define TARGET_VERSION="$(python -c "print(\"py${TARGET_PYTHON}\".replace(\".\", \"\"))")" --define VERSION="$(cat version/version.txt)"  :tesseract_decoder_wheel
 
     - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4

BUILD

@@ -13,6 +13,8 @@ filegroup(
     visibility = ["//visibility:public"],
 )
 
+MANYLINUX_VERSION="manylinux_2_17_x86_64.manylinux2014_x86_64"
+
 py_wheel(
     name="tesseract_decoder_wheel",
     distribution = "tesseract_decoder",
@@ -26,9 +28,10 @@ py_wheel(
     ],
     python_tag="$(TARGET_VERSION)",
     platform= select({
-        "@platforms//os:macos": "macosx_10_13_x86_64",
+        ":macos_arm": "macosx_11_0_arm64",
+        ":macos_x86": "macosx_10_13_x86_64",
         "@platforms//os:windows": "win32",
-        "@platforms//os:linux": "manylinux_2_17_x86_64.manylinux2014_x86_64",
+        "@platforms//os:linux": MANYLINUX_VERSION,
     }),
     strip_path_prefixes = ["src"],
     description_file=":package_description",
@@ -37,3 +40,19 @@ py_wheel(
     author="The Tesseract Decoder Authors.",
     homepage="https://github.com/quantumlib/tesseract-decoder",
 )
+
+config_setting(
+    name = "macos_arm",
+    constraint_values = [
+        "@platforms//os:macos",
+        "@platforms//cpu:arm64",
+    ],
+)
+
+config_setting(
+    name = "macos_x86",
+    constraint_values = [
+        "@platforms//os:macos",
+        "@platforms//cpu:x86_64",
+    ],
+)

WORKSPACE

@@ -66,3 +66,22 @@ http_archive(
     urls = ["https://github.com/bazelbuild/platforms/archive/refs/tags/0.0.6.zip"],
     strip_prefix = "platforms-0.0.6",
 )
+
+
+
+
+BOOST_VERSION = "1.83.0"
+BOOST_ARCHIVE_NAME = "boost_{}".format(BOOST_VERSION.replace(".", "_"))
+
+http_archive(
+    name = "boost",
+    urls = [
+        "https://archives.boost.io/release/{}/source/{}.tar.gz".format(
+            BOOST_VERSION,
+            BOOST_ARCHIVE_NAME,
+        )
+    ],
+    strip_prefix = BOOST_ARCHIVE_NAME,
+    sha256 = "c0685b68dd44cc46574cce86c4e17c0f611b15e195be9848dfd0769a0a207628",
+    build_file = "//external:boost.BUILD",
+)

external/boost.BUILD

@@ -0,0 +1,16 @@
+# external/boost.BUILD
+package(default_visibility = ["//visibility:public"])
+
+# A cc_library for the Boost headers themselves.
+cc_library(
+    name = "boost_headers",
+    hdrs = glob(["boost/**/*.hpp"]),
+    includes = ["."],
+)
+
+# A specific target for dynamic_bitset, which is header-only
+# and depends on the main headers.
+cc_library(
+    name = "dynamic_bitset",
+    deps = [":boost_headers"],
+)

src/BUILD

@@ -121,6 +121,7 @@ cc_library(
     linkopts = OPT_LINKOPTS,
     deps = [
         ":libutils",
+        "@boost//:dynamic_bitset",
     ],
 )
 

src/tesseract.cc

@@ -15,7 +15,9 @@
 #include "tesseract.h"
 
 #include <algorithm>
+#include <boost/functional/hash.hpp>  // For boost::hash_range
 #include <cassert>
+#include <functional>  // For std::hash (though not strictly necessary here, but good practice)
 #include <iostream>
 
 namespace {
@@ -37,6 +39,17 @@ std::ostream& operator<<(std::ostream& os, const std::vector<T>& vec) {
 
 };  // namespace
 
+namespace std {
+template <>
+struct hash<boost::dynamic_bitset<>> {
+  size_t operator()(const boost::dynamic_bitset<>& bs) const {
+    // Delegate to Boost's internal hash_value for dynamic_bitset
+    // This is the correct and most efficient way.
+    return boost::hash_value(bs);
+  }
+};
+}  // namespace std
+
 std::string TesseractConfig::str() {
   auto& config = *this;
   std::stringstream ss;
@@ -73,7 +86,7 @@ double TesseractDecoder::get_detcost(
   ErrorCost ec;
   DetectorCostTuple dct;
 
-  for (size_t ei : d2e[d]) {
+  for (int ei : d2e[d]) {
     ec = error_costs[ei];
     if (ec.min_cost >= min_cost) break;
 
@@ -89,17 +102,6 @@ double TesseractDecoder::get_detcost(
   return min_cost + config.det_penalty;
 }
 
-struct VectorCharHash {
-  size_t operator()(const std::vector<char>& v) const {
-    size_t seed = v.size();
-
-    for (char el : v) {
-      seed = seed * 31 + static_cast<size_t>(el);
-    }
-    return seed;
-  }
-};
-
 TesseractDecoder::TesseractDecoder(TesseractConfig config_) : config(config_) {
   config.dem = common::remove_zero_probability_errors(config.dem);
   if (config.det_orders.empty()) {
@@ -206,7 +208,7 @@ void TesseractDecoder::decode_to_errors(const std::vector<uint64_t>& detections)
 }
 
 void TesseractDecoder::flip_detectors_and_block_errors(
-    size_t detector_order, const std::vector<size_t>& errors, std::vector<char>& detectors,
+    size_t detector_order, const std::vector<size_t>& errors, boost::dynamic_bitset<>& detectors,
     std::vector<DetectorCostTuple>& detector_cost_tuples) const {
   for (size_t ei : errors) {
     size_t min_detector = std::numeric_limits<size_t>::max();
@@ -217,15 +219,15 @@ void TesseractDecoder::flip_detectors_and_block_errors(
       }
     }
 
-    for (size_t oei : d2e[min_detector]) {
+    for (int oei : d2e[min_detector]) {
       detector_cost_tuples[oei].error_blocked = 1;
       if (!config.at_most_two_errors_per_detector && oei == ei) break;
     }
 
-    for (size_t d : edets[ei]) {
+    for (int d : edets[ei]) {
       detectors[d] = !detectors[d];
       if (!detectors[d] && config.at_most_two_errors_per_detector) {
-        for (size_t oei : d2e[d]) {
+        for (int oei : d2e[d]) {
           detector_cost_tuples[oei].error_blocked = 1;
         }
       }
@@ -239,10 +241,9 @@ void TesseractDecoder::decode_to_errors(const std::vector<uint64_t>& detections,
   low_confidence_flag = false;
 
   std::priority_queue<Node, std::vector<Node>, std::greater<Node>> pq;
-  std::unordered_map<size_t, std::unordered_set<std::vector<char>, VectorCharHash>>
-      visited_detectors;
+  std::unordered_map<size_t, std::unordered_set<boost::dynamic_bitset<>>> visited_detectors;
 
-  std::vector<char> initial_detectors(num_detectors, false);
+  boost::dynamic_bitset<> initial_detectors(num_detectors, false);
   std::vector<DetectorCostTuple> initial_detector_cost_tuples(num_errors);
 
   for (size_t d : detections) {
@@ -266,7 +267,7 @@ void TesseractDecoder::decode_to_errors(const std::vector<uint64_t>& detections,
   size_t max_num_detectors = min_num_detectors + detector_beam;
 
   std::vector<size_t> next_errors;
-  std::vector<char> next_detectors;
+  boost::dynamic_bitset<> next_detectors;
   std::vector<DetectorCostTuple> next_detector_cost_tuples;
 
   pq.push({initial_cost, min_num_detectors, std::vector<size_t>()});
@@ -278,7 +279,7 @@ void TesseractDecoder::decode_to_errors(const std::vector<uint64_t>& detections,
 
     if (node.num_detectors > max_num_detectors) continue;
 
-    std::vector<char> detectors = initial_detectors;
+    boost::dynamic_bitset<> detectors = initial_detectors;
     std::vector<DetectorCostTuple> detector_cost_tuples(num_errors);
     flip_detectors_and_block_errors(detector_order, node.errors, detectors, detector_cost_tuples);
 
@@ -363,7 +364,7 @@ void TesseractDecoder::decode_to_errors(const std::vector<uint64_t>& detections,
     size_t prev_ei = std::numeric_limits<size_t>::max();
     std::vector<double> detector_cost_cache(num_detectors, -1);
 
-    for (size_t ei : d2e[min_detector]) {
+    for (int ei : d2e[min_detector]) {
       if (detector_cost_tuples[ei].error_blocked) continue;
 
       if (prev_ei != std::numeric_limits<size_t>::max()) {
@@ -398,7 +399,7 @@ void TesseractDecoder::decode_to_errors(const std::vector<uint64_t>& detections,
         }
 
         if (!next_detectors[d] && config.at_most_two_errors_per_detector) {
-          for (size_t oei : d2e[d]) {
+          for (int oei : d2e[d]) {
             next_detector_cost_tuples[oei].error_blocked =
                 next_detector_cost_tuples[oei].error_blocked == 1
                     ? 1
@@ -426,7 +427,7 @@ void TesseractDecoder::decode_to_errors(const std::vector<uint64_t>& detections,
         }
       }
 
-      for (size_t od : eneighbors[ei]) {
+      for (int od : eneighbors[ei]) {
         if (!detectors[od] || !next_detectors[od]) continue;
         if (detector_cost_cache[od] == -1) {
           detector_cost_cache[od] = get_detcost(od, detector_cost_tuples);

src/tesseract.h

@@ -15,6 +15,7 @@
 #ifndef TESSERACT_DECODER_H
 #define TESSERACT_DECODER_H
 
+#include <boost/dynamic_bitset.hpp>
 #include <queue>
 #include <string>
 #include <unordered_map>
@@ -101,7 +102,7 @@ struct TesseractDecoder {
   void initialize_structures(size_t num_detectors);
   double get_detcost(size_t d, const std::vector<DetectorCostTuple>& detector_cost_tuples) const;
   void flip_detectors_and_block_errors(size_t detector_order, const std::vector<size_t>& errors,
-                                       std::vector<char>& detectors,
+                                       boost::dynamic_bitset<>& detectors,
                                        std::vector<DetectorCostTuple>& detector_cost_tuples) const;
 };