Move unit-parsing code to src/lib/confmgt

lib/confmgt is at a higher level than lib/conf, since it needs to
call down to logging and similar modules.

8 files changed, 267 insertions, 193 deletions

diff --git a/.gitignore b/.gitignore
index 0865f981b1..77610b3193 100644
--- a/.gitignore
+++ b/.gitignore
@@ -162,6 +162,8 @@ uptime-*.json
 /src/lib/libtor-buf-testing.a
 /src/lib/libtor-compress.a
 /src/lib/libtor-compress-testing.a
+/src/lib/libtor-confmgt.a
+/src/lib/libtor-confmgt-testing.a
 /src/lib/libtor-container.a
 /src/lib/libtor-container-testing.a
 /src/lib/libtor-crypt-ops.a
diff --git a/Makefile.am b/Makefile.am
index df30e0b59a..0083608ce9 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -54,6 +54,7 @@ TOR_UTIL_LIBS = \
 	src/lib/libtor-math.a \
 	src/lib/libtor-meminfo.a \
 	src/lib/libtor-osinfo.a \
+	src/lib/libtor-confmgt.a \
 	src/lib/libtor-log.a \
 	src/lib/libtor-lock.a \
 	src/lib/libtor-fdio.a \
@@ -88,6 +89,7 @@ TOR_UTIL_TESTING_LIBS = \
 	src/lib/libtor-meminfo-testing.a \
 	src/lib/libtor-osinfo-testing.a \
 	src/lib/libtor-term-testing.a \
+	src/lib/libtor-confmgt-testing.a \
 	src/lib/libtor-log-testing.a \
 	src/lib/libtor-lock-testing.a \
 	src/lib/libtor-fdio-testing.a \
diff --git a/src/app/config/confparse.c b/src/app/config/confparse.c
index 3bf14b378d..296e7c2a39 100644
--- a/src/app/config/confparse.c
+++ b/src/app/config/confparse.c
@@ -26,12 +26,10 @@
 #include "app/config/confparse.h"
 #include "feature/nodelist/routerset.h"
 
+#include "lib/confmgt/unitparse.h"
 #include "lib/container/bitarray.h"
 #include "lib/encoding/confline.h"
 
-static uint64_t config_parse_memunit(const char *s, int *ok);
-static int config_parse_msec_interval(const char *s, int *ok);
-static int config_parse_interval(const char *s, int *ok);
 static void config_reset(const config_format_t *fmt, void *options,
                          const config_var_t *var, int use_defaults);
 
@@ -1014,193 +1012,3 @@ config_dump(const config_format_t *fmt, const void *default_options,
   }
   return result;
 }
-
-/** Mapping from a unit name to a multiplier for converting that unit into a
- * base unit.  Used by config_parse_unit. */
-struct unit_table_t {
-  const char *unit; /**< The name of the unit */
-  uint64_t multiplier; /**< How many of the base unit appear in this unit */
-};
-
-/** Table to map the names of memory units to the number of bytes they
- * contain. */
-static struct unit_table_t memory_units[] = {
-  { "",          1 },
-  { "b",         1<< 0 },
-  { "byte",      1<< 0 },
-  { "bytes",     1<< 0 },
-  { "kb",        1<<10 },
-  { "kbyte",     1<<10 },
-  { "kbytes",    1<<10 },
-  { "kilobyte",  1<<10 },
-  { "kilobytes", 1<<10 },
-  { "kilobits",  1<<7  },
-  { "kilobit",   1<<7  },
-  { "kbits",     1<<7  },
-  { "kbit",      1<<7  },
-  { "m",         1<<20 },
-  { "mb",        1<<20 },
-  { "mbyte",     1<<20 },
-  { "mbytes",    1<<20 },
-  { "megabyte",  1<<20 },
-  { "megabytes", 1<<20 },
-  { "megabits",  1<<17 },
-  { "megabit",   1<<17 },
-  { "mbits",     1<<17 },
-  { "mbit",      1<<17 },
-  { "gb",        1<<30 },
-  { "gbyte",     1<<30 },
-  { "gbytes",    1<<30 },
-  { "gigabyte",  1<<30 },
-  { "gigabytes", 1<<30 },
-  { "gigabits",  1<<27 },
-  { "gigabit",   1<<27 },
-  { "gbits",     1<<27 },
-  { "gbit",      1<<27 },
-  { "tb",        UINT64_C(1)<<40 },
-  { "tbyte",     UINT64_C(1)<<40 },
-  { "tbytes",    UINT64_C(1)<<40 },
-  { "terabyte",  UINT64_C(1)<<40 },
-  { "terabytes", UINT64_C(1)<<40 },
-  { "terabits",  UINT64_C(1)<<37 },
-  { "terabit",   UINT64_C(1)<<37 },
-  { "tbits",     UINT64_C(1)<<37 },
-  { "tbit",      UINT64_C(1)<<37 },
-  { NULL, 0 },
-};
-
-/** Table to map the names of time units to the number of seconds they
- * contain. */
-static struct unit_table_t time_units[] = {
-  { "",         1 },
-  { "second",   1 },
-  { "seconds",  1 },
-  { "minute",   60 },
-  { "minutes",  60 },
-  { "hour",     60*60 },
-  { "hours",    60*60 },
-  { "day",      24*60*60 },
-  { "days",     24*60*60 },
-  { "week",     7*24*60*60 },
-  { "weeks",    7*24*60*60 },
-  { "month",    2629728, }, /* about 30.437 days */
-  { "months",   2629728, },
-  { NULL, 0 },
-};
-
-/** Table to map the names of time units to the number of milliseconds
- * they contain. */
-static struct unit_table_t time_msec_units[] = {
-  { "",         1 },
-  { "msec",     1 },
-  { "millisecond", 1 },
-  { "milliseconds", 1 },
-  { "second",   1000 },
-  { "seconds",  1000 },
-  { "minute",   60*1000 },
-  { "minutes",  60*1000 },
-  { "hour",     60*60*1000 },
-  { "hours",    60*60*1000 },
-  { "day",      24*60*60*1000 },
-  { "days",     24*60*60*1000 },
-  { "week",     7*24*60*60*1000 },
-  { "weeks",    7*24*60*60*1000 },
-  { NULL, 0 },
-};
-
-/** Parse a string <b>val</b> containing a number, zero or more
- * spaces, and an optional unit string.  If the unit appears in the
- * table <b>u</b>, then multiply the number by the unit multiplier.
- * On success, set *<b>ok</b> to 1 and return this product.
- * Otherwise, set *<b>ok</b> to 0.
- */
-static uint64_t
-config_parse_units(const char *val, struct unit_table_t *u, int *ok)
-{
-  uint64_t v = 0;
-  double d = 0;
-  int use_float = 0;
-  char *cp;
-
-  tor_assert(ok);
-
-  v = tor_parse_uint64(val, 10, 0, UINT64_MAX, ok, &cp);
-  if (!*ok || (cp && *cp == '.')) {
-    d = tor_parse_double(val, 0, (double)UINT64_MAX, ok, &cp);
-    if (!*ok)
-      goto done;
-    use_float = 1;
-  }
-
-  if (!cp) {
-    *ok = 1;
-    v = use_float ? ((uint64_t)d) :  v;
-    goto done;
-  }
-
-  cp = (char*) eat_whitespace(cp);
-
-  for ( ;u->unit;++u) {
-    if (!strcasecmp(u->unit, cp)) {
-      if (use_float)
-        v = (uint64_t)(u->multiplier * d);
-      else
-        v *= u->multiplier;
-      *ok = 1;
-      goto done;
-    }
-  }
-  log_warn(LD_CONFIG, "Unknown unit '%s'.", cp);
-  *ok = 0;
- done:
-
-  if (*ok)
-    return v;
-  else
-    return 0;
-}
-
-/** Parse a string in the format "number unit", where unit is a unit of
- * information (byte, KB, M, etc).  On success, set *<b>ok</b> to true
- * and return the number of bytes specified.  Otherwise, set
- * *<b>ok</b> to false and return 0. */
-static uint64_t
-config_parse_memunit(const char *s, int *ok)
-{
-  uint64_t u = config_parse_units(s, memory_units, ok);
-  return u;
-}
-
-/** Parse a string in the format "number unit", where unit is a unit of
- * time in milliseconds.  On success, set *<b>ok</b> to true and return
- * the number of milliseconds in the provided interval.  Otherwise, set
- * *<b>ok</b> to 0 and return -1. */
-static int
-config_parse_msec_interval(const char *s, int *ok)
-{
-  uint64_t r;
-  r = config_parse_units(s, time_msec_units, ok);
-  if (r > INT_MAX) {
-    log_warn(LD_CONFIG, "Msec interval '%s' is too long", s);
-    *ok = 0;
-    return -1;
-  }
-  return (int)r;
-}
-
-/** Parse a string in the format "number unit", where unit is a unit of time.
- * On success, set *<b>ok</b> to true and return the number of seconds in
- * the provided interval.  Otherwise, set *<b>ok</b> to 0 and return -1.
- */
-static int
-config_parse_interval(const char *s, int *ok)
-{
-  uint64_t r;
-  r = config_parse_units(s, time_units, ok);
-  if (r > INT_MAX) {
-    log_warn(LD_CONFIG, "Interval '%s' is too long", s);
-    *ok = 0;
-    return -1;
-  }
-  return (int)r;
-}
diff --git a/src/include.am b/src/include.am
index ab1983b3cd..065bdc31cb 100644
--- a/src/include.am
+++ b/src/include.am
@@ -6,6 +6,7 @@ include src/lib/cc/include.am
 include src/lib/ctime/include.am
 include src/lib/compress/include.am
 include src/lib/conf/include.am
+include src/lib/confmgt/include.am
 include src/lib/container/include.am
 include src/lib/crypt_ops/include.am
 include src/lib/defs/include.am
diff --git a/src/lib/confmgt/.may_include b/src/lib/confmgt/.may_include
new file mode 100644
index 0000000000..640acf3770
--- /dev/null
+++ b/src/lib/confmgt/.may_include
@@ -0,0 +1,7 @@
+orconfig.h
+lib/cc/*.h
+lib/conf/*.h
+lib/confmgt/*.h
+lib/log/*.h
+lib/malloc/*.h
+lib/string/*.h
diff --git a/src/lib/confmgt/include.am b/src/lib/confmgt/include.am
new file mode 100644
index 0000000000..729e6147ff
--- /dev/null
+++ b/src/lib/confmgt/include.am
@@ -0,0 +1,18 @@
+noinst_LIBRARIES += src/lib/libtor-confmgt.a
+
+if UNITTESTS_ENABLED
+noinst_LIBRARIES += src/lib/libtor-confmgt-testing.a
+endif
+
+# ADD_C_FILE: INSERT SOURCES HERE.
+src_lib_libtor_confmgt_a_SOURCES =			\
+	src/lib/confmgt/unitparse.c
+
+src_lib_libtor_confmgt_testing_a_SOURCES = \
+	$(src_lib_libtor_confmgt_a_SOURCES)
+src_lib_libtor_confmgt_testing_a_CPPFLAGS = $(AM_CPPFLAGS) $(TEST_CPPFLAGS)
+src_lib_libtor_confmgt_testing_a_CFLAGS = $(AM_CFLAGS) $(TEST_CFLAGS)
+
+# ADD_C_FILE: INSERT HEADERS HERE.
+noinst_HEADERS +=					\
+	src/lib/confmgt/unitparse.h
diff --git a/src/lib/confmgt/unitparse.c b/src/lib/confmgt/unitparse.c
new file mode 100644
index 0000000000..906195259d
--- /dev/null
+++ b/src/lib/confmgt/unitparse.c
@@ -0,0 +1,202 @@
+/* Copyright (c) 2001 Matej Pfajfar.
+ * Copyright (c) 2001-2004, Roger Dingledine.
+ * Copyright (c) 2004-2006, Roger Dingledine, Nick Mathewson.
+ * Copyright (c) 2007-2019, The Tor Project, Inc. */
+/* See LICENSE for licensing information */
+
+/**
+ * @file unitparse.c
+ * @brief Functions for parsing values with units from a configuration file.
+ **/
+
+#include "orconfig.h"
+#include "lib/confmgt/unitparse.h"
+#include "lib/log/log.h"
+#include "lib/log/util_bug.h"
+#include "lib/string/parse_int.h"
+#include "lib/string/util_string.h"
+
+#include <string.h>
+
+/** Table to map the names of memory units to the number of bytes they
+ * contain. */
+const struct unit_table_t memory_units[] = {
+  { "",          1 },
+  { "b",         1<< 0 },
+  { "byte",      1<< 0 },
+  { "bytes",     1<< 0 },
+  { "kb",        1<<10 },
+  { "kbyte",     1<<10 },
+  { "kbytes",    1<<10 },
+  { "kilobyte",  1<<10 },
+  { "kilobytes", 1<<10 },
+  { "kilobits",  1<<7  },
+  { "kilobit",   1<<7  },
+  { "kbits",     1<<7  },
+  { "kbit",      1<<7  },
+  { "m",         1<<20 },
+  { "mb",        1<<20 },
+  { "mbyte",     1<<20 },
+  { "mbytes",    1<<20 },
+  { "megabyte",  1<<20 },
+  { "megabytes", 1<<20 },
+  { "megabits",  1<<17 },
+  { "megabit",   1<<17 },
+  { "mbits",     1<<17 },
+  { "mbit",      1<<17 },
+  { "gb",        1<<30 },
+  { "gbyte",     1<<30 },
+  { "gbytes",    1<<30 },
+  { "gigabyte",  1<<30 },
+  { "gigabytes", 1<<30 },
+  { "gigabits",  1<<27 },
+  { "gigabit",   1<<27 },
+  { "gbits",     1<<27 },
+  { "gbit",      1<<27 },
+  { "tb",        UINT64_C(1)<<40 },
+  { "tbyte",     UINT64_C(1)<<40 },
+  { "tbytes",    UINT64_C(1)<<40 },
+  { "terabyte",  UINT64_C(1)<<40 },
+  { "terabytes", UINT64_C(1)<<40 },
+  { "terabits",  UINT64_C(1)<<37 },
+  { "terabit",   UINT64_C(1)<<37 },
+  { "tbits",     UINT64_C(1)<<37 },
+  { "tbit",      UINT64_C(1)<<37 },
+  { NULL, 0 },
+};
+
+/** Table to map the names of time units to the number of seconds they
+ * contain. */
+const struct unit_table_t time_units[] = {
+  { "",         1 },
+  { "second",   1 },
+  { "seconds",  1 },
+  { "minute",   60 },
+  { "minutes",  60 },
+  { "hour",     60*60 },
+  { "hours",    60*60 },
+  { "day",      24*60*60 },
+  { "days",     24*60*60 },
+  { "week",     7*24*60*60 },
+  { "weeks",    7*24*60*60 },
+  { "month",    2629728, }, /* about 30.437 days */
+  { "months",   2629728, },
+  { NULL, 0 },
+};
+
+/** Table to map the names of time units to the number of milliseconds
+ * they contain. */
+const struct unit_table_t time_msec_units[] = {
+  { "",         1 },
+  { "msec",     1 },
+  { "millisecond", 1 },
+  { "milliseconds", 1 },
+  { "second",   1000 },
+  { "seconds",  1000 },
+  { "minute",   60*1000 },
+  { "minutes",  60*1000 },
+  { "hour",     60*60*1000 },
+  { "hours",    60*60*1000 },
+  { "day",      24*60*60*1000 },
+  { "days",     24*60*60*1000 },
+  { "week",     7*24*60*60*1000 },
+  { "weeks",    7*24*60*60*1000 },
+  { NULL, 0 },
+};
+
+/** Parse a string <b>val</b> containing a number, zero or more
+ * spaces, and an optional unit string.  If the unit appears in the
+ * table <b>u</b>, then multiply the number by the unit multiplier.
+ * On success, set *<b>ok</b> to 1 and return this product.
+ * Otherwise, set *<b>ok</b> to 0.
+ */
+uint64_t
+config_parse_units(const char *val, const unit_table_t *u, int *ok)
+{
+  uint64_t v = 0;
+  double d = 0;
+  int use_float = 0;
+  char *cp;
+
+  tor_assert(ok);
+
+  v = tor_parse_uint64(val, 10, 0, UINT64_MAX, ok, &cp);
+  if (!*ok || (cp && *cp == '.')) {
+    d = tor_parse_double(val, 0, (double)UINT64_MAX, ok, &cp);
+    if (!*ok)
+      goto done;
+    use_float = 1;
+  }
+
+  if (!cp) {
+    *ok = 1;
+    v = use_float ? ((uint64_t)d) :  v;
+    goto done;
+  }
+
+  cp = (char*) eat_whitespace(cp);
+
+  for ( ;u->unit;++u) {
+    if (!strcasecmp(u->unit, cp)) {
+      if (use_float)
+        v = (uint64_t)(u->multiplier * d);
+      else
+        v *= u->multiplier;
+      *ok = 1;
+      goto done;
+    }
+  }
+  log_warn(LD_CONFIG, "Unknown unit '%s'.", cp);
+  *ok = 0;
+ done:
+
+  if (*ok)
+    return v;
+  else
+    return 0;
+}
+
+/** Parse a string in the format "number unit", where unit is a unit of
+ * information (byte, KB, M, etc).  On success, set *<b>ok</b> to true
+ * and return the number of bytes specified.  Otherwise, set
+ * *<b>ok</b> to false and return 0. */
+uint64_t
+config_parse_memunit(const char *s, int *ok)
+{
+  uint64_t u = config_parse_units(s, memory_units, ok);
+  return u;
+}
+
+/** Parse a string in the format "number unit", where unit is a unit of
+ * time in milliseconds.  On success, set *<b>ok</b> to true and return
+ * the number of milliseconds in the provided interval.  Otherwise, set
+ * *<b>ok</b> to 0 and return -1. */
+int
+config_parse_msec_interval(const char *s, int *ok)
+{
+  uint64_t r;
+  r = config_parse_units(s, time_msec_units, ok);
+  if (r > INT_MAX) {
+    log_warn(LD_CONFIG, "Msec interval '%s' is too long", s);
+    *ok = 0;
+    return -1;
+  }
+  return (int)r;
+}
+
+/** Parse a string in the format "number unit", where unit is a unit of time.
+ * On success, set *<b>ok</b> to true and return the number of seconds in
+ * the provided interval.  Otherwise, set *<b>ok</b> to 0 and return -1.
+ */
+int
+config_parse_interval(const char *s, int *ok)
+{
+  uint64_t r;
+  r = config_parse_units(s, time_units, ok);
+  if (r > INT_MAX) {
+    log_warn(LD_CONFIG, "Interval '%s' is too long", s);
+    *ok = 0;
+    return -1;
+  }
+  return (int)r;
+}
diff --git a/src/lib/confmgt/unitparse.h b/src/lib/confmgt/unitparse.h
new file mode 100644
index 0000000000..216361a7d4
--- /dev/null
+++ b/src/lib/confmgt/unitparse.h
@@ -0,0 +1,34 @@
+/* Copyright (c) 2001 Matej Pfajfar.
+ * Copyright (c) 2001-2004, Roger Dingledine.
+ * Copyright (c) 2004-2006, Roger Dingledine, Nick Mathewson.
+ * Copyright (c) 2007-2019, The Tor Project, Inc. */
+/* See LICENSE for licensing information */
+
+/**
+ * @file unitparse.h
+ * @brief Header for lib/confmgt/unitparse.c
+ **/
+
+#ifndef TOR_LIB_CONFMGT_UNITPARSE_H
+#define TOR_LIB_CONFMGT_UNITPARSE_H
+
+#include <lib/cc/torint.h>
+
+/** Mapping from a unit name to a multiplier for converting that unit into a
+ * base unit.  Used by config_parse_unit. */
+typedef struct unit_table_t {
+  const char *unit; /**< The name of the unit */
+  uint64_t multiplier; /**< How many of the base unit appear in this unit */
+} unit_table_t;
+
+extern const unit_table_t memory_units[];
+extern const unit_table_t time_units[];
+extern const struct unit_table_t time_msec_units[];
+
+uint64_t config_parse_units(const char *val, const unit_table_t *u, int *ok);
+
+uint64_t config_parse_memunit(const char *s, int *ok);
+int config_parse_msec_interval(const char *s, int *ok);
+int config_parse_interval(const char *s, int *ok);
+
+#endif /* !defined(TOR_LIB_CONFMGT_UNITPARSE_H) */