Merge pull request #599 from jeromekelleher/dumpload-fileobj

Dump/load from file objects

Author: mergify[bot]

c/CHANGELOG.rst

@@ -55,6 +55,9 @@ In development.
 - Tables loaded from a file can now be edited in the same way as any other
   table collection (:user:`jeromekelleher`, :issue:`536`, :pr:`530`.
 
+- Support for reading/writing to arbitrary file streams with the loadf/dumpf
+  variants for tree sequence and table collection load/dump
+  (:user:`jeromekelleher`, :user:`grahamgower`, :issue:`565`, :pr:`599`).
 
 **Deprecated**
 

c/examples/Makefile

@@ -1,5 +1,5 @@
 # Simple Makefile for building examples.
-# This will build the examples in the current directory by compiling in the 
+# This will build the examples in the current directory by compiling in the
 # full tskit source into each of the examples. This is *not* recommended for
 # real projects!
 #
@@ -8,28 +8,31 @@
 #
 # **Note**: This repo uses git submodules, and these must be checked out
 # correctly for this makefile to work, e.g.:
-# 
+#
 # $ git clone [email protected]:tskit-dev/tskit.git --recurse-submodules
-# 
+#
 # See the documentation (https://tskit.readthedocs.io/en/stable/c-api.html)
-# for more details on how to use the C API, and the tskit build examples 
-# repo (https://github.com/tskit-dev/tskit-build-examples) for examples 
+# for more details on how to use the C API, and the tskit build examples
+# repo (https://github.com/tskit-dev/tskit-build-examples) for examples
 # of how to set up a production-ready build with tskit.
 #
 
 CFLAGS=-I../ -I../subprojects/kastore
 TSKIT_SOURCE=../tskit/*.c ../subprojects/kastore/kastore.c
 
-all: tree_iteration haploid_wright_fisher tree_traversal
+all: tree_iteration haploid_wright_fisher tree_traversal streaming
+
+tree_iteration: tree_iteration.c
+	${CC} ${CFLAGS} -o $@ $< ${TSKIT_SOURCE} -lm
 
-tree_iteration: tree_iteration.c 
+tree_traversal: tree_traversal.c
 	${CC} ${CFLAGS} -o $@ $< ${TSKIT_SOURCE} -lm
 
-tree_traversal: tree_traversal.c 
+streaming: streaming.c
 	${CC} ${CFLAGS} -o $@ $< ${TSKIT_SOURCE} -lm
 
 # This needs GSL
-haploid_wright_fisher: haploid_wright_fisher.c 
+haploid_wright_fisher: haploid_wright_fisher.c
 	${CC} ${CFLAGS} -o $@ $< ${TSKIT_SOURCE} -lgsl -lgslcblas -lm
 
 clean:

c/examples/streaming.c

@@ -0,0 +1,37 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <tskit/tables.h>
+
+#define check_tsk_error(val)                                                            \
+    if (val < 0) {                                                                      \
+        fprintf(stderr, "Error: line %d: %s\n", __LINE__, tsk_strerror(val));           \
+        exit(EXIT_FAILURE);                                                             \
+    }
+
+int
+main(int argc, char **argv)
+{
+    int ret;
+    int j = 0;
+    tsk_table_collection_t tables;
+
+    ret = tsk_table_collection_init(&tables, 0);
+    check_tsk_error(ret);
+
+    while (true) {
+        ret = tsk_table_collection_loadf(&tables, stdin, TSK_NO_INIT);
+        if (ret == TSK_ERR_EOF) {
+            break;
+        }
+        check_tsk_error(ret);
+        fprintf(stderr, "Tree sequence %d had %d mutations\n", j,
+            (int) tables.mutations.num_rows);
+        ret = tsk_mutation_table_truncate(&tables.mutations, 0);
+        check_tsk_error(ret);
+        ret = tsk_table_collection_dumpf(&tables, stdout, 0);
+        check_tsk_error(ret);
+        j++;
+    }
+    tsk_table_collection_free(&tables);
+    return EXIT_SUCCESS;
+}

c/meson.build

@@ -99,6 +99,8 @@ if not meson.is_subproject()
         sources: ['examples/tree_iteration.c'], link_with: [tskit_lib], dependencies: lib_deps)
     executable('tree_traversal',
         sources: ['examples/tree_traversal.c'], link_with: [tskit_lib], dependencies: lib_deps)
+    executable('streaming',
+        sources: ['examples/streaming.c'], link_with: [tskit_lib], dependencies: lib_deps)
 
     gsl_dep = dependency('gsl', required: false)
     if gsl_dep.found()

c/tests/meson-subproject/example.c

@@ -52,7 +52,7 @@ test_load_error()
     printf("test_open_error\n");
     tsk_treeseq_t ts;
     int ret = tsk_treeseq_load(&ts, "no such file", 0);
-    assert(tsk_is_kas_error(ret));
+    assert(ret == TSK_ERR_IO);
     tsk_treeseq_free(&ts);
 }
 

c/tests/test_core.c

@@ -47,7 +47,7 @@ test_strerror(void)
 static void
 test_strerror_kastore(void)
 {
-    int kastore_errors[] = { KAS_ERR_NO_MEMORY, KAS_ERR_IO, KAS_ERR_KEY_NOT_FOUND };
+    int kastore_errors[] = { KAS_ERR_NO_MEMORY, KAS_ERR_KEY_NOT_FOUND };
     size_t j;
     int err;