Slow5 (#298)

* Added slow5 parser

* add package docs

* add better flow as suggested by  matiasinsaurralde

* Nearly entire rewrite of parser

* Added variable failure reasons

* Add stringbuilder for raw signals

* fixed lint issues.

* update specification link

* separate example file

* Comment where example.slow5 comes from

---------

Co-authored-by: Timothy Stiles <[email protected]>

io/slow5/data/header_tests/test_header_not_enough_attributes.slow5

@@ -0,0 +1,3 @@
+#slow5_version	0.2.0
+#num_read_groups	2
+@asic_id	4175987214

io/slow5/data/header_tests/test_header_numReadGroups_bad.slow5

@@ -0,0 +1,3 @@
+#slow5_version	0.2.0
+#num_read_groups	bad!
+@asic_id	4175987214

io/slow5/data/header_tests/test_header_without_tabs.slow5

@@ -0,0 +1,4 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@bad
+@asic_id	4175987214

io/slow5/data/read_tests/continue.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	.	bad	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/digitisation.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	bad	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/endReason.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{bad,unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/end_reason.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	bad	10
+

io/slow5/data/read_tests/end_reason_unknown.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	1000	10
+

io/slow5/data/read_tests/len_raw_signal.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	bad	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/median_before.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	bad	5	10
+

io/slow5/data/read_tests/offset.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	bad	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/range.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	bad	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/raw_signal.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,bad,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/read_group.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	bad	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/read_number.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	bad	1	219.133423	5	10
+

io/slow5/data/read_tests/sampling_rate.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	raw	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/start_mux.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	bad	219.133423	5	10
+

io/slow5/data/read_tests/start_time.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	bad	5383	1	219.133423	5	10
+

io/slow5/data/read_tests/unknown.slow5

@@ -0,0 +1,6 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number	bad
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10	1

io/slow5/data/test_example.slow5

@@ -0,0 +1,7 @@
+#slow5_version	0.2.0
+#num_read_groups	1
+@asic_id	4175987214
+#char*	uint32_t	double	double	double	double	uint64_t	int16_t*	uint64_t	int32_t	uint8_t	double	enum{unknown,partial,mux_change,unblock_mux_change,data_service_unblock_mux_change,signal_positive,signal_negative}	char*
+#read_id	read_group	digitisation	offset	range	sampling_rate	len_raw_signal	raw_signal	start_time	read_number	start_mux	median_before	end_reason	channel_number
+0026631e-33a3-49ab-aa22-3ab157d71f8b	0	8192	16	1489.52832	4000	5347	430,472,463	8318394	5383	1	219.133423	5	10
+

io/slow5/example_test.go

@@ -0,0 +1,32 @@
+package slow5_test
+
+import (
+	"fmt"
+	"os"
+
+	"github.com/TimothyStiles/poly/io/slow5"
+)
+
+func ExampleNewParser() {
+	// example.slow5 is a file I generated using slow5tools from nanopore fast5
+	// run where I was testing using nanopore for doing COVID testing. It
+	// contains real nanopore data.
+	file, _ := os.Open("data/example.slow5")
+	// Set maxLineSize to 64kb. If you expect longer reads,
+	// make maxLineSize longer!
+	const maxLineSize = 2 * 32 * 1024
+	parser, _, _ := slow5.NewParser(file, maxLineSize)
+
+	var outputReads []slow5.Read
+	for {
+		read, err := parser.ParseNext()
+		if err != nil {
+			// Break at EOF
+			break
+		}
+		outputReads = append(outputReads, read)
+	}
+
+	fmt.Println(outputReads[0].RawSignal[0:10])
+	// Output: [430 472 463 467 454 465 463 450 450 449]
+}