Bumping version prior to v2.0.2

CHANGELOG.md

@@ -1,6 +1,18 @@
 # falco changelog
 
-## falco 2.0.1 (2026-08-03)
+## falco 2.0.2 (2026-09-09)
+
+Changes:
+* Input for preseq: falco can output a file (`outdir/preseq_hist.txt`) that
+  can be directly input to preseq for library complexity analysis.
+* Building on macOS: code updates for easier building using Apple Clang on
+  macOS.
+* Standard input: Falco can now accept piped or redirected input from stdin in
+  either SAM or FASTQ format (thanks to @kerrycobb for initiating this).
+* HTML report: for reads longer than 1000 bp, plots in the HTML will have
+  bases grouped to prevent generating very large, slow and unreadable HTML.
+
+## falco 2.0.1 (2026-08-12)
 
 Changes:
 * GC content distribution across reads now smoothing more similarly to falco v1

CMakeLists.txt

@@ -4,7 +4,7 @@
 # $ cmake --version
 cmake_minimum_required(VERSION 3.30)
 project(falco
-  VERSION 2.0.1
+  VERSION 2.0.2
   DESCRIPTION "A tool to assess the quality of sequence read data"
   HOMEPAGE_URL https://github.com/smithlabcode/falco
   LANGUAGES CXX

data/test_data/md5sum.txt

@@ -1,17 +1,17 @@
-f59cf622d7d36b9d2f1170e6d63438ab  bam_mult_out/bam_1/fastqc_data.txt
-6318172912a6b7f9d348ce7b0b0618ed  bam_mult_out/bam_2/fastqc_data.txt
-f59cf622d7d36b9d2f1170e6d63438ab  bam_orig_dups_out/bam_1/fastqc_data.txt
-f59cf622d7d36b9d2f1170e6d63438ab  bam_out/bam_1/fastqc_data.txt
-f59cf622d7d36b9d2f1170e6d63438ab  bam_tiles_out/bam_1/fastqc_data.txt
-c2d51938c568b3c224efe9134baddb03  fastq_bgzf_mult_out/fastq_bgzip_1/fastqc_data.txt
-eb09f6189fbb1519d87d3c349d0be279  fastq_bgzf_mult_out/fastq_bgzip_2/fastqc_data.txt
-c2d51938c568b3c224efe9134baddb03  fastq_bgzf_out/fastq_bgzip_1/fastqc_data.txt
-c2d51938c568b3c224efe9134baddb03  fastq_bgzf_threads_out/fastq_bgzip_1/fastqc_data.txt
-5d74ecab5efbdb35e775e969411cbda4  fastq_gz_out/fastq_gz_1/fastqc_data.txt
-be637ed4a4ebf2f1a64edf30ef1f8bb8  fastq_plain_out/fastq_1/fastqc_data.txt
-bc8fd6e40a0ca55cb00634bc306a896c  groups_out/bam_1/fastqc_data.txt
-a1952ae366bd7c7207f40db833b1d16b  sam_out/sam_1/fastqc_data.txt
-3fe18e2ee85e3912ede8c57559bf9f88  preseq_out/bam_1/preseq_hist.txt
-045639456fbe4a81b5de2789ceb95ddd  bam_kmers_out/bam_1/fastqc_data.txt
-a1aa02211d63f507646a9e12122f0226  sam_stdin_out/sam_stdin/fastqc_data.txt
-c61e37d2c8d64b6950a5dad300e5fd60  fastq_stdin_out/fastq_stdin/fastqc_data.txt
+64cd41bd26bfd42e234fc3799bf245e8  bam_tiles_out/bam_1/fastqc_data.txt
+ef8c02aec6745200ffef3355981e8f04  bam_kmers_out/bam_1/fastqc_data.txt
+dc3aeeffd19458cec93b93d0a8c61bee  fastq_gz_out/fastq_gz_1/fastqc_data.txt
+55ce06b400bf48023a45d05aa997539d  groups_out/bam_1/fastqc_data.txt
+e1493086c5ddaedf20ec61f8c7a80ba4  fastq_stdin_out/fastq_stdin/fastqc_data.txt
+64cd41bd26bfd42e234fc3799bf245e8  preseq_out/bam_1/fastqc_data.txt
+1fa22a239dc71e99d0b4387c20a146e7  sam_out/sam_1/fastqc_data.txt
+64cd41bd26bfd42e234fc3799bf245e8  bam_out/bam_1/fastqc_data.txt
+7c047f91119eee2922c293c7881be1ff  fastq_bgzf_threads_out/fastq_bgzip_1/fastqc_data.txt
+244963d5c9c1dbcf609d879408611de8  fastq_bgzf_mult_out/fastq_bgzip_2/fastqc_data.txt
+7c047f91119eee2922c293c7881be1ff  fastq_bgzf_mult_out/fastq_bgzip_1/fastqc_data.txt
+64cd41bd26bfd42e234fc3799bf245e8  bam_orig_dups_out/bam_1/fastqc_data.txt
+64cd41bd26bfd42e234fc3799bf245e8  bam_mult_out/bam_1/fastqc_data.txt
+a5107edbcf8b22e443e0e2940a189ce2  bam_mult_out/bam_2/fastqc_data.txt
+7c047f91119eee2922c293c7881be1ff  fastq_bgzf_out/fastq_bgzip_1/fastqc_data.txt
+b8bee551c09cdfd885a76cc231c90cb6  sam_stdin_out/sam_stdin/fastqc_data.txt
+1e726d61c68092876e40fca069b788b2  fastq_plain_out/fastq_1/fastqc_data.txt

src/adapter_matcher.cpp

@@ -121,7 +121,7 @@ adapter_matcher::html(const std::uint64_t n_reads,
 Plotly.newPlot("adapters_plot",
 {},
 {{
-xaxis: {{title: "Base position"}},
+xaxis: {{title: "Base position", automargin: true}},
 yaxis: {{title: "% sequences with adapter before position"}},
 }});
 </script>)";

src/falco.cpp

@@ -38,6 +38,12 @@ Output files will be created in "results/SRX081761".  Reading from stdin
 disables tile analysis. To re-enable it, specify either 4 or 6 to indicate
 position of the tile id in read names.  Example: "--stdin fq:4"
 
+Group bases in the output:
+$ falco --groups -o results SRX081761_1.fastq
+Output is summarized in base position groups after the first 9 bp. As in FastQC,
+grouping is done before grading and therefore impacts grades. If reads exceed
+1000 bp grouping is done automatically in HTML files without impacting grades.
+
 Default configuration files can be found here:
 {}
 Use these as templates. Copy and modify them to customize your analysis.
@@ -116,7 +122,7 @@ write_output(
   for (const auto [result, info, outdir] :
        std::views::zip(results, infos, outdirs)) {
     const auto outdir_path = std::filesystem::path{outdir};
-    const auto summary = results_summary(std::move(result), mode, info);
+    auto summary = results_summary(std::move(result), mode, info);
     write_file(outdir_path / report_filename, summary.get_report());
     write_file(outdir_path / html_filename, summary.get_html());
     write_file(outdir_path / summary_filename, summary.get_summary());
@@ -396,7 +402,7 @@ main(int argc, char *argv[]) {
         infiles_opt->expected(1);
       },
       "Read from stdin assuming given format (see help)")
-      ->option_text("fq|sam[:{4,6}]")
+      ->option_text("fq|sam[:N]")
       ->delimiter(':')
       ->allow_extra_args(false)
       ->type_size(1, 2)
@@ -419,7 +425,8 @@ main(int argc, char *argv[]) {
       }, "Use original duplication mode (enables --dups)")
       ->excludes(preseq_opt)
       ->option_text(" ");
-    app.add_flag("--groups", do_groups, "Group base positions in output")
+    app.add_flag("--groups", do_groups,
+                 "Group base positions in output (see help)")
       ->option_text(" ");
     app.add_flag("--tiles,!--no-tiles", do_tiles,
                  "Toggle per-tile quality analysis (default: on)")

src/html.cpp

@@ -29,7 +29,8 @@
 #include <span>
 #include <stdexcept>
 #include <string>
-#include <tuple>  // for std::get probably in fmt
+#include <tuple>    // for std::get probably in fmt
+#include <utility>  // for pair
 #include <vector>
 
 [[nodiscard]] auto
@@ -86,8 +87,8 @@ sequence_length_html(const std::vector<std::uint64_t> &lengths,
 Plotly.newPlot("length_plot",
 [{}],
 {{
-xaxis: {{title: "Sequence length"}},
-yaxis: {{title: "Number of sequences"}},
+xaxis: {{title: "Sequence length", automargin: true}},
+yaxis: {{title: "Number of sequences", automargin: true}},
 }});
 </script>
 )";
@@ -125,7 +126,7 @@ Plotly.newPlot("gc_sequence_plot",
 [{}],
 {{
 xaxis: {{title: "% GC"}},
-yaxis: {{title: "Density"}}
+yaxis: {{title: "Density", automargin: true}}
 }});
 </script>
 )";
@@ -168,7 +169,7 @@ sequence_html(const std::vector<falco::nuc_array> &nucs,
 Plotly.newPlot("sequence_plot",
 [{}],
 {{
-xaxis: {{title: "Base position"}},
+xaxis: {{title: "Base position", automargin: true}},
 yaxis: {{title: "Per base sequence content", range: [0, 100]}},
 }});
 </script>
@@ -228,7 +229,7 @@ line: {{color: "red"}},
 name: "Fraction of N reads per base"
 }}],
 {{
-xaxis: {{title: "Base position"}},
+xaxis: {{title: "Base position", automargin: true}},
 yaxis: {{title: "% N", range: [0, 100]}},
 }}
 );</script>
@@ -272,7 +273,7 @@ line: {{color: "red"}},
 name: "Sequence quality distribution"
 }}],
 {{
-xaxis: {{title: "Phred quality", range: [0, 40]}},
+xaxis: {{title: "Phred quality", range: [0, 40], automargin: true}},
 yaxis: {{title: "Density", rangemode: "tozero"}},
 }});
 </script>
@@ -308,7 +309,7 @@ Plotly.newPlot("quality_base_plot",
 [{}],
 {{
 showlegend: false,
-xaxis: {{title: "Base position"}},
+xaxis: {{title: "Base position", automargin: true}},
 yaxis: {{title: "Phred quality", rangemode: "tozero"}},
 }});
 </script>
@@ -326,6 +327,7 @@ yaxis: {{title: "Phred quality", rangemode: "tozero"}},
       return "yellow";
     return "green";
   };
+  assert(std::size(qual) == std::size(groups));
   std::vector<std::string> lines;
   for (const auto [idx, q] : falco::views::enumerate(qual)) {
     const auto fq = five_quants(q);
@@ -379,8 +381,8 @@ basic_stats_html(const file_info &info, const std::uint64_t n_reads,
 
 [[nodiscard]] auto
 tile_html(const tile_processor::tiles_centered_t &centered,
-          const std::vector<base_group_t> &groups, const file_grades &grades)
-  -> std::string {
+          const std::vector<base_group_t> &groups,
+          const file_grades &grades) -> std::string {
   static constexpr auto label = "tile";
   static constexpr auto n_quants = 20.0;
   // ADS: ??? (-10: red, 0: light blue, +10: dark blue)
@@ -399,7 +401,7 @@ showscale: true,
 }}],
 {{
 showlegend: false,
-xaxis: {{title: "Base position"}},
+xaxis: {{title: "Base position", automargin: true}},
 yaxis: {{title: "tile", type: "category"}},
 }}
 )""";
@@ -425,6 +427,7 @@ yaxis: {{title: "tile", type: "category"}},
   };
   const auto z = std::views::transform(centered | std::views::values, format1);
 
+  assert(std::size(std::cbegin(centered)->second) == std::size(groups));
   const auto grade = grades.grade(label);
   const auto title = grades.get_title(label);
   return fmt::format(
@@ -439,8 +442,8 @@ yaxis: {{title: "tile", type: "category"}},
 }
 
 [[nodiscard]] auto
-kmer_html(const std::vector<kmer_result> &results, const file_grades &grades)
-  -> std::string {
+kmer_html(const std::vector<kmer_result> &results,
+          const file_grades &grades) -> std::string {
   static constexpr auto label = "kmer";
   static constexpr auto plot_format = R"(<div id="kmer_plot"></div>
 <script>Plotly.newPlot("kmer_plot",

src/html.hpp

@@ -16,6 +16,8 @@ struct file_grades;
 struct kmer_result;
 struct file_info;
 
+static constexpr auto html_readlen_cutoff = 1000;
+
 // grade / section_label / section_title / grade / text
 static constexpr auto html_module_fmt =
   R"(<div class="module">

src/results_summary.cpp

@@ -172,14 +172,23 @@ results_summary::get_report() const -> std::string {
 }
 
 [[nodiscard]] auto
-results_summary::get_html() const -> std::string {
+results_summary::get_html() -> std::string {
   const auto basic_stats =
     basic_stats_html(info, n_reads, min_read_len, max_read_len, median_read_len,
                      total_gc, total_bases, grades);
   auto sections = std::unordered_map<std::string, std::string>{
     {"basic_stats", basic_stats},
   };
 
+  if (!mode.do_groups() && max_read_len > html_readlen_cutoff) {
+    mode.set_do_groups(1);
+    apply_groups();
+    // ADS: this below is not good. The issues related to different groupings
+    // for the grading and report, vs. the HTML, need to be handled better
+    // overall.
+    centered = tp.get_centered();
+  }
+
   if (mode.do_adap())
     sections.emplace("adapter", am.html(n_reads, max_read_len, groups, grades));
 

src/results_summary.hpp

@@ -80,7 +80,7 @@ struct results_summary {
   get_report() const -> std::string;
 
   [[nodiscard]] auto
-  get_html() const -> std::string;
+  get_html() -> std::string;
 
   [[nodiscard]] auto
   get_summary() const -> std::string;