minimap2 0.2.22.0 → 0.2.24.1

data/ext/minimap2/kalloc.c

@@ -0,0 +1,205 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "kalloc.h"
+
+/* In kalloc, a *core* is a large chunk of contiguous memory. Each core is
+ * associated with a master header, which keeps the size of the current core
+ * and the pointer to next core. Kalloc allocates small *blocks* of memory from
+ * the cores and organizes free memory blocks in a circular single-linked list.
+ *
+ * In the following diagram, "@" stands for the header of a free block (of type
+ * header_t), "#" for the header of an allocated block (of type size_t), "-"
+ * for free memory, and "+" for allocated memory.
+ *
+ * master        This region is core 1.          master           This region is core 2.
+ *      |                                             |
+ *      *@-------#++++++#++++++++++++@--------        *@----------#++++++++++++#+++++++@------------
+ *       |                           |                 |                               |
+ *       p=p->ptr->ptr->ptr->ptr     p->ptr            p->ptr->ptr                     p->ptr->ptr->ptr
+ */
+typedef struct header_t {
+	size_t size;
+	struct header_t *ptr;
+} header_t;
+
+typedef struct {
+	void *par;
+	size_t min_core_size;
+	header_t base, *loop_head, *core_head; /* base is a zero-sized block always kept in the loop */
+} kmem_t;
+
+static void panic(const char *s)
+{
+	fprintf(stderr, "%s\n", s);
+	abort();
+}
+
+void *km_init2(void *km_par, size_t min_core_size)
+{
+	kmem_t *km;
+	km = (kmem_t*)kcalloc(km_par, 1, sizeof(kmem_t));
+	km->par = km_par;
+	km->min_core_size = min_core_size > 0? min_core_size : 0x80000;
+	return (void*)km;
+}
+
+void *km_init(void) { return km_init2(0, 0); }
+
+void km_destroy(void *_km)
+{
+	kmem_t *km = (kmem_t*)_km;
+	void *km_par;
+	header_t *p, *q;
+	if (km == NULL) return;
+	km_par = km->par;
+	for (p = km->core_head; p != NULL;) {
+		q = p->ptr;
+		kfree(km_par, p);
+		p = q;
+	}
+	kfree(km_par, km);
+}
+
+static header_t *morecore(kmem_t *km, size_t nu)
+{
+	header_t *q;
+	size_t bytes, *p;
+	nu = (nu + 1 + (km->min_core_size - 1)) / km->min_core_size * km->min_core_size; /* the first +1 for core header */
+	bytes = nu * sizeof(header_t);
+	q = (header_t*)kmalloc(km->par, bytes);
+	if (!q) panic("[morecore] insufficient memory");
+	q->ptr = km->core_head, q->size = nu, km->core_head = q;
+	p = (size_t*)(q + 1);
+	*p = nu - 1; /* the size of the free block; -1 because the first unit is used for the core header */
+	kfree(km, p + 1); /* initialize the new "core"; NB: the core header is not looped. */
+	return km->loop_head;
+}
+
+void kfree(void *_km, void *ap) /* kfree() also adds a new core to the circular list */
+{
+	header_t *p, *q;
+	kmem_t *km = (kmem_t*)_km;
+	
+	if (!ap) return;
+	if (km == NULL) {
+		free(ap);
+		return;
+	}
+	p = (header_t*)((size_t*)ap - 1);
+	p->size = *((size_t*)ap - 1);
+	/* Find the pointer that points to the block to be freed. The following loop can stop on two conditions:
+	 *
+	 * a) "p>q && p<q->ptr": @------#++++++++#+++++++@-------    @---------------#+++++++@-------
+	 *    (can also be in    |      |                |        -> |                       |
+	 *     two cores)        q      p           q->ptr           q                  q->ptr
+	 *
+	 *                       @--------    #+++++++++@--------    @--------    @------------------
+	 *                       |            |         |         -> |            |
+	 *                       q            p    q->ptr            q       q->ptr
+	 *
+	 * b) "q>=q->ptr && (p>q || p<q->ptr)":  @-------#+++++   @--------#+++++++     @-------#+++++   @----------------
+	 *                                       |                |        |         -> |                |
+	 *                                  q->ptr                q        p       q->ptr                q
+	 *
+	 *                                       #+++++++@-----   #++++++++@-------     @-------------   #++++++++@-------
+	 *                                       |       |                 |         -> |                         |
+	 *                                       p  q->ptr                 q       q->ptr                         q
+	 */
+	for (q = km->loop_head; !(p > q && p < q->ptr); q = q->ptr)
+		if (q >= q->ptr && (p > q || p < q->ptr)) break;
+	if (p + p->size == q->ptr) { /* two adjacent blocks, merge p and q->ptr (the 2nd and 4th cases) */
+		p->size += q->ptr->size;
+		p->ptr = q->ptr->ptr;
+	} else if (p + p->size > q->ptr && q->ptr >= p) {
+		panic("[kfree] The end of the allocated block enters a free block.");
+	} else p->ptr = q->ptr; /* backup q->ptr */
+
+	if (q + q->size == p) { /* two adjacent blocks, merge q and p (the other two cases) */
+		q->size += p->size;
+		q->ptr = p->ptr;
+		km->loop_head = q;
+	} else if (q + q->size > p && p >= q) {
+		panic("[kfree] The end of a free block enters the allocated block.");
+	} else km->loop_head = p, q->ptr = p; /* in two cores, cannot be merged; create a new block in the list */
+}
+
+void *kmalloc(void *_km, size_t n_bytes)
+{
+	kmem_t *km = (kmem_t*)_km;
+	size_t n_units;
+	header_t *p, *q;
+
+	if (n_bytes == 0) return 0;
+	if (km == NULL) return malloc(n_bytes);
+	n_units = (n_bytes + sizeof(size_t) + sizeof(header_t) - 1) / sizeof(header_t); /* header+n_bytes requires at least this number of units */
+
+	if (!(q = km->loop_head)) /* the first time when kmalloc() is called, intialize it */
+		q = km->loop_head = km->base.ptr = &km->base;
+	for (p = q->ptr;; q = p, p = p->ptr) { /* search for a suitable block */
+		if (p->size >= n_units) { /* p->size if the size of current block. This line means the current block is large enough. */
+			if (p->size == n_units) q->ptr = p->ptr; /* no need to split the block */
+			else { /* split the block. NB: memory is allocated at the end of the block! */
+				p->size -= n_units; /* reduce the size of the free block */
+				p += p->size; /* p points to the allocated block */
+				*(size_t*)p = n_units; /* set the size */
+			}
+			km->loop_head = q; /* set the end of chain */
+			return (size_t*)p + 1;
+		}
+		if (p == km->loop_head) { /* then ask for more "cores" */
+			if ((p = morecore(km, n_units)) == 0) return 0;
+		}
+	}
+}
+
+void *kcalloc(void *_km, size_t count, size_t size)
+{
+	kmem_t *km = (kmem_t*)_km;
+	void *p;
+	if (size == 0 || count == 0) return 0;
+	if (km == NULL) return calloc(count, size);
+	p = kmalloc(km, count * size);
+	memset(p, 0, count * size);
+	return p;
+}
+
+void *krealloc(void *_km, void *ap, size_t n_bytes) // TODO: this can be made more efficient in principle
+{
+	kmem_t *km = (kmem_t*)_km;
+	size_t cap, *p, *q;
+
+	if (n_bytes == 0) {
+		kfree(km, ap); return 0;
+	}
+	if (km == NULL) return realloc(ap, n_bytes);
+	if (ap == NULL) return kmalloc(km, n_bytes);
+	p = (size_t*)ap - 1;
+	cap = (*p) * sizeof(header_t) - sizeof(size_t);
+	if (cap >= n_bytes) return ap; /* TODO: this prevents shrinking */
+	q = (size_t*)kmalloc(km, n_bytes);
+	memcpy(q, ap, cap);
+	kfree(km, ap);
+	return q;
+}
+
+void km_stat(const void *_km, km_stat_t *s)
+{
+	kmem_t *km = (kmem_t*)_km;
+	header_t *p;
+	memset(s, 0, sizeof(km_stat_t));
+	if (km == NULL || km->loop_head == NULL) return;
+	for (p = km->loop_head;; p = p->ptr) {
+		s->available += p->size * sizeof(header_t);
+		if (p->size != 0) ++s->n_blocks; /* &kmem_t::base is always one of the cores. It is zero-sized. */
+		if (p->ptr > p && p + p->size > p->ptr)
+			panic("[km_stat] The end of a free block enters another free block.");
+		if (p->ptr == km->loop_head) break;
+	}
+	for (p = km->core_head; p != NULL; p = p->ptr) {
+		size_t size = p->size * sizeof(header_t);
+		++s->n_cores;
+		s->capacity += size;
+		s->largest = s->largest > size? s->largest : size;
+	}
+}

data/ext/minimap2/kalloc.h

@@ -0,0 +1,76 @@
+#ifndef _KALLOC_H_
+#define _KALLOC_H_
+
+#include <stddef.h> /* for size_t */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+	size_t capacity, available, n_blocks, n_cores, largest;
+} km_stat_t;
+
+void *kmalloc(void *km, size_t size);
+void *krealloc(void *km, void *ptr, size_t size);
+void *kcalloc(void *km, size_t count, size_t size);
+void kfree(void *km, void *ptr);
+
+void *km_init(void);
+void *km_init2(void *km_par, size_t min_core_size);
+void km_destroy(void *km);
+void km_stat(const void *_km, km_stat_t *s);
+
+#ifdef __cplusplus
+}
+#endif
+
+#define KMALLOC(km, ptr, len) ((ptr) = (__typeof__(ptr))kmalloc((km), (len) * sizeof(*(ptr))))
+#define KCALLOC(km, ptr, len) ((ptr) = (__typeof__(ptr))kcalloc((km), (len), sizeof(*(ptr))))
+#define KREALLOC(km, ptr, len) ((ptr) = (__typeof__(ptr))krealloc((km), (ptr), (len) * sizeof(*(ptr))))
+
+#define KEXPAND(km, a, m) do { \
+		(m) = (m) >= 4? (m) + ((m)>>1) : 16; \
+		KREALLOC((km), (a), (m)); \
+	} while (0)
+
+#ifndef klib_unused
+#if (defined __clang__ && __clang_major__ >= 3) || (defined __GNUC__ && __GNUC__ >= 3)
+#define klib_unused __attribute__ ((__unused__))
+#else
+#define klib_unused
+#endif
+#endif /* klib_unused */
+
+#define KALLOC_POOL_INIT2(SCOPE, name, kmptype_t) \
+	typedef struct { \
+		size_t cnt, n, max; \
+		kmptype_t **buf; \
+		void *km; \
+	} kmp_##name##_t; \
+	SCOPE kmp_##name##_t *kmp_init_##name(void *km) { \
+		kmp_##name##_t *mp; \
+		KCALLOC(km, mp, 1); \
+		mp->km = km; \
+		return mp; \
+	} \
+	SCOPE void kmp_destroy_##name(kmp_##name##_t *mp) { \
+		size_t k; \
+		for (k = 0; k < mp->n; ++k) kfree(mp->km, mp->buf[k]); \
+		kfree(mp->km, mp->buf); kfree(mp->km, mp); \
+	} \
+	SCOPE kmptype_t *kmp_alloc_##name(kmp_##name##_t *mp) { \
+		++mp->cnt; \
+		if (mp->n == 0) return (kmptype_t*)kcalloc(mp->km, 1, sizeof(kmptype_t)); \
+		return mp->buf[--mp->n]; \
+	} \
+	SCOPE void kmp_free_##name(kmp_##name##_t *mp, kmptype_t *p) { \
+		--mp->cnt; \
+		if (mp->n == mp->max) KEXPAND(mp->km, mp->buf, mp->max); \
+		mp->buf[mp->n++] = p; \
+	}
+
+#define KALLOC_POOL_INIT(name, kmptype_t) \
+	KALLOC_POOL_INIT2(static inline klib_unused, name, kmptype_t)
+
+#endif

data/ext/minimap2/kdq.h

@@ -0,0 +1,132 @@
+#ifndef __AC_KDQ_H
+#define __AC_KDQ_H
+
+#include <stdlib.h>
+#include <string.h>
+#include <stdint.h>
+#include "kalloc.h"
+
+#define __KDQ_TYPE(type) \
+	typedef struct { \
+		uint64_t front:58, bits:6, count, mask; \
+		type *a; \
+		void *km; \
+	} kdq_##type##_t;
+
+#define kdq_t(type) kdq_##type##_t
+#define kdq_size(q) ((q)->count)
+#define kdq_first(q) ((q)->a[(q)->front])
+#define kdq_last(q) ((q)->a[((q)->front + (q)->count - 1) & (q)->mask])
+#define kdq_at(q, i) ((q)->a[((q)->front + (i)) & (q)->mask])
+
+#define __KDQ_IMPL(type, SCOPE) \
+	SCOPE kdq_##type##_t *kdq_init_##type(void *km) \
+	{ \
+		kdq_##type##_t *q; \
+		q = (kdq_##type##_t*)kcalloc(km, 1, sizeof(kdq_##type##_t)); \
+		q->bits = 2, q->mask = (1ULL<<q->bits) - 1; \
+		q->a = (type*)kmalloc(km, (1<<q->bits) * sizeof(type)); \
+		q->km = km; \
+		return q; \
+	} \
+	SCOPE void kdq_destroy_##type(kdq_##type##_t *q) \
+	{ \
+		if (q == 0) return; \
+		kfree(q->km, q->a); kfree(q->km, q); \
+	} \
+	SCOPE int kdq_resize_##type(kdq_##type##_t *q, int new_bits) \
+	{ \
+		size_t new_size = 1ULL<<new_bits, old_size = 1ULL<<q->bits; \
+		if (new_size < q->count) { /* not big enough */ \
+			int i; \
+			for (i = 0; i < 64; ++i) \
+				if (1ULL<<i > q->count) break; \
+			new_bits = i, new_size = 1ULL<<new_bits; \
+		} \
+		if (new_bits == q->bits) return q->bits; /* unchanged */ \
+		if (new_bits > q->bits) q->a = (type*)krealloc(q->km, q->a, (1ULL<<new_bits) * sizeof(type)); \
+		if (q->front + q->count <= old_size) { /* unwrapped */ \
+			if (q->front + q->count > new_size) /* only happens for shrinking */ \
+				memmove(q->a, q->a + new_size, (q->front + q->count - new_size) * sizeof(type)); \
+		} else { /* wrapped */ \
+			memmove(q->a + (new_size - (old_size - q->front)), q->a + q->front, (old_size - q->front) * sizeof(type)); \
+			q->front = new_size - (old_size - q->front); \
+		} \
+		q->bits = new_bits, q->mask = (1ULL<<q->bits) - 1; \
+		if (new_bits < q->bits) q->a = (type*)krealloc(q->km, q->a, (1ULL<<new_bits) * sizeof(type)); \
+		return q->bits; \
+	} \
+	SCOPE type *kdq_pushp_##type(kdq_##type##_t *q) \
+	{ \
+		if (q->count == 1ULL<<q->bits) kdq_resize_##type(q, q->bits + 1); \
+		return &q->a[((q->count++) + q->front) & (q)->mask]; \
+	} \
+	SCOPE void kdq_push_##type(kdq_##type##_t *q, type v) \
+	{ \
+		if (q->count == 1ULL<<q->bits) kdq_resize_##type(q, q->bits + 1); \
+		q->a[((q->count++) + q->front) & (q)->mask] = v; \
+	} \
+	SCOPE type *kdq_unshiftp_##type(kdq_##type##_t *q) \
+	{ \
+		if (q->count == 1ULL<<q->bits) kdq_resize_##type(q, q->bits + 1); \
+		++q->count; \
+		q->front = q->front? q->front - 1 : (1ULL<<q->bits) - 1; \
+		return &q->a[q->front]; \
+	} \
+	SCOPE void kdq_unshift_##type(kdq_##type##_t *q, type v) \
+	{ \
+		type *p; \
+		p = kdq_unshiftp_##type(q); \
+		*p = v; \
+	} \
+	SCOPE type *kdq_pop_##type(kdq_##type##_t *q) \
+	{ \
+		return q->count? &q->a[((--q->count) + q->front) & q->mask] : 0; \
+	} \
+	SCOPE type *kdq_shift_##type(kdq_##type##_t *q) \
+	{ \
+		type *d = 0; \
+		if (q->count == 0) return 0; \
+		d = &q->a[q->front++]; \
+		q->front &= q->mask; \
+		--q->count; \
+		return d; \
+	}
+
+#define KDQ_INIT2(type, SCOPE) \
+	__KDQ_TYPE(type) \
+	__KDQ_IMPL(type, SCOPE)
+
+#ifndef klib_unused
+#if (defined __clang__ && __clang_major__ >= 3) || (defined __GNUC__ && __GNUC__ >= 3)
+#define klib_unused __attribute__ ((__unused__))
+#else
+#define klib_unused
+#endif
+#endif /* klib_unused */
+
+#define KDQ_INIT(type) KDQ_INIT2(type, static inline klib_unused)
+
+#define KDQ_DECLARE(type) \
+	__KDQ_TYPE(type) \
+	kdq_##type##_t *kdq_init_##type(); \
+	void kdq_destroy_##type(kdq_##type##_t *q); \
+	int kdq_resize_##type(kdq_##type##_t *q, int new_bits); \
+	type *kdq_pushp_##type(kdq_##type##_t *q); \
+	void kdq_push_##type(kdq_##type##_t *q, type v); \
+	type *kdq_unshiftp_##type(kdq_##type##_t *q); \
+	void kdq_unshift_##type(kdq_##type##_t *q, type v); \
+	type *kdq_pop_##type(kdq_##type##_t *q); \
+	type *kdq_shift_##type(kdq_##type##_t *q);
+
+#define kdq_init(type, km) kdq_init_##type(km)
+#define kdq_destroy(type, q) kdq_destroy_##type(q)
+#define kdq_resize(type, q, new_bits) kdq_resize_##type(q, new_bits)
+#define kdq_pushp(type, q) kdq_pushp_##type(q)
+#define kdq_push(type, q, v) kdq_push_##type(q, v)
+#define kdq_pop(type, q) kdq_pop_##type(q)
+#define kdq_unshiftp(type, q) kdq_unshiftp_##type(q)
+#define kdq_unshift(type, q, v) kdq_unshift_##type(q, v)
+#define kdq_shift(type, q) kdq_shift_##type(q)
+
+#endif

data/ext/minimap2/ketopt.h

@@ -0,0 +1,120 @@
+#ifndef KETOPT_H
+#define KETOPT_H
+
+#include <string.h> /* for strchr() and strncmp() */
+
+#define ko_no_argument       0
+#define ko_required_argument 1
+#define ko_optional_argument 2
+
+typedef struct {
+	int ind;   /* equivalent to optind */
+	int opt;   /* equivalent to optopt */
+	char *arg; /* equivalent to optarg */
+	int longidx; /* index of a long option; or -1 if short */
+	/* private variables not intended for external uses */
+	int i, pos, n_args;
+} ketopt_t;
+
+typedef struct {
+	char *name;
+	int has_arg;
+	int val;
+} ko_longopt_t;
+
+static ketopt_t KETOPT_INIT = { 1, 0, 0, -1, 1, 0, 0 };
+
+static void ketopt_permute(char *argv[], int j, int n) /* move argv[j] over n elements to the left */
+{
+	int k;
+	char *p = argv[j];
+	for (k = 0; k < n; ++k)
+		argv[j - k] = argv[j - k - 1];
+	argv[j - k] = p;
+}
+
+/**
+ * Parse command-line options and arguments
+ *
+ * This fuction has a similar interface to GNU's getopt_long(). Each call
+ * parses one option and returns the option name.  s->arg points to the option
+ * argument if present. The function returns -1 when all command-line arguments
+ * are parsed. In this case, s->ind is the index of the first non-option
+ * argument.
+ *
+ * @param s         status; shall be initialized to KETOPT_INIT on the first call
+ * @param argc      length of argv[]
+ * @param argv      list of command-line arguments; argv[0] is ignored
+ * @param permute   non-zero to move options ahead of non-option arguments
+ * @param ostr      option string
+ * @param longopts  long options
+ *
+ * @return ASCII for a short option; ko_longopt_t::val for a long option; -1 if
+ *         argv[] is fully processed; '?' for an unknown option or an ambiguous
+ *         long option; ':' if an option argument is missing
+ */
+static int ketopt(ketopt_t *s, int argc, char *argv[], int permute, const char *ostr, const ko_longopt_t *longopts)
+{
+	int opt = -1, i0, j;
+	if (permute) {
+		while (s->i < argc && (argv[s->i][0] != '-' || argv[s->i][1] == '\0'))
+			++s->i, ++s->n_args;
+	}
+	s->arg = 0, s->longidx = -1, i0 = s->i;
+	if (s->i >= argc || argv[s->i][0] != '-' || argv[s->i][1] == '\0') {
+		s->ind = s->i - s->n_args;
+		return -1;
+	}
+	if (argv[s->i][0] == '-' && argv[s->i][1] == '-') { /* "--" or a long option */
+		if (argv[s->i][2] == '\0') { /* a bare "--" */
+			ketopt_permute(argv, s->i, s->n_args);
+			++s->i, s->ind = s->i - s->n_args;
+			return -1;
+		}
+		s->opt = 0, opt = '?', s->pos = -1;
+		if (longopts) { /* parse long options */
+			int k, n_exact = 0, n_partial = 0;
+			const ko_longopt_t *o = 0, *o_exact = 0, *o_partial = 0;
+			for (j = 2; argv[s->i][j] != '\0' && argv[s->i][j] != '='; ++j) {} /* find the end of the option name */
+			for (k = 0; longopts[k].name != 0; ++k)
+				if (strncmp(&argv[s->i][2], longopts[k].name, j - 2) == 0) {
+					if (longopts[k].name[j - 2] == 0) ++n_exact, o_exact = &longopts[k];
+					else ++n_partial, o_partial = &longopts[k];
+				}
+			if (n_exact > 1 || (n_exact == 0 && n_partial > 1)) return '?';
+			o = n_exact == 1? o_exact : n_partial == 1? o_partial : 0;
+			if (o) {
+				s->opt = opt = o->val, s->longidx = o - longopts;
+				if (argv[s->i][j] == '=') s->arg = &argv[s->i][j + 1];
+				if (o->has_arg == 1 && argv[s->i][j] == '\0') {
+					if (s->i < argc - 1) s->arg = argv[++s->i];
+					else opt = ':'; /* missing option argument */
+				}
+			}
+		}
+	} else { /* a short option */
+		char *p;
+		if (s->pos == 0) s->pos = 1;
+		opt = s->opt = argv[s->i][s->pos++];
+		p = strchr((char*)ostr, opt);
+		if (p == 0) {
+			opt = '?'; /* unknown option */
+		} else if (p[1] == ':') {
+			if (argv[s->i][s->pos] == 0) {
+				if (s->i < argc - 1) s->arg = argv[++s->i];
+				else opt = ':'; /* missing option argument */
+			} else s->arg = &argv[s->i][s->pos];
+			s->pos = -1;
+		}
+	}
+	if (s->pos < 0 || argv[s->i][s->pos] == 0) {
+		++s->i, s->pos = 0;
+		if (s->n_args > 0) /* permute */
+			for (j = i0; j < s->i; ++j)
+				ketopt_permute(argv, j, s->n_args);
+	}
+	s->ind = s->i - s->n_args;
+	return opt;
+}
+
+#endif