Add a reader flag to disable generated blank label avoidance

5 files changed, 30 insertions, 10 deletions

diff --git a/doc/man/serd-pipe.1 b/doc/man/serd-pipe.1
index 0ce40dbd..a986c570 100644
--- a/doc/man/serd-pipe.1
+++ b/doc/man/serd-pipe.1
@@ -111,6 +111,14 @@ so that URI references and blank nodes are passed to the sink exactly as they ar
 Note that this does not apply to CURIEs, since serd deliberately does not
 have a way to represent CURIE nodes.
 A bad namespace prefix is considered a syntax error.
+.It Cm generated
+Read seemingly generated blank node labels exactly without adjusting them.
+Normally, blank node labels like
+.Li b123
+are adapted to avoid potential clashes with generated ones.
+This flag disables that,
+so such labels will be passed through exactly as they are in the input.
+Note that this may corrupt the output by merging distinct blank nodes.
 .El
 .It Fl O Ar syntax
 Set an output syntax or option.
diff --git a/include/serd/reader.h b/include/serd/reader.h
index e25565cb..d62428cf 100644
--- a/include/serd/reader.h
+++ b/include/serd/reader.h
@@ -67,6 +67,21 @@ typedef enum {
      a syntax error.
   */
   SERD_READ_VERBATIM = 1U << 2U,
+
+  /**
+     Read generated blank node labels exactly without adjusting them.
+
+     Normally, the reader will adapt blank node labels in the input that clash
+     with its scheme for generating new ones, for example mapping "_:b123" to
+     "_:B123".  This flag disables that, so that blank node labels are passed
+     to the sink exactly as they are in the input.
+
+     Note that this flag should be used carefully, since it can result in data
+     corruption.  Specifically, if the input is a syntax like Turtle with
+     anonymous nodes, the generated IDs for those nodes may clash with IDs from
+     the input document.
+  */
+  SERD_READ_GENERATED = 1U << 3U,
 } SerdReaderFlag;
 
 /// Bitwise OR of SerdReaderFlag values
diff --git a/src/read_ntriples.c b/src/read_ntriples.c
index 7a43e4c2..57b1e7be 100644
--- a/src/read_ntriples.c
+++ b/src/read_ntriples.c
@@ -17,7 +17,6 @@
 #include "serd/caret.h"
 #include "serd/sink.h"
 #include "serd/statement.h"
-#include "serd/syntax.h"
 
 #include <assert.h>
 #include <stdbool.h>
@@ -237,22 +236,18 @@ read_STRING_LITERAL(SerdReader* const reader,
   return tolerate_status(reader, st) ? SERD_SUCCESS : st;
 }
 
-static bool
-avoid_blank_clashes(const SerdReader* const reader)
-{
-  return (reader->syntax == SERD_TURTLE || reader->syntax == SERD_TRIG) &&
-         !(reader->flags & SERD_READ_VERBATIM);
-}
-
 static SerdStatus
 adjust_blank_id(SerdReader* const reader, char* const buf)
 {
-  if (avoid_blank_clashes(reader) && is_digit(buf[reader->bprefix_len + 1])) {
+  if (!(reader->flags & SERD_READ_GENERATED) &&
+      is_digit(buf[reader->bprefix_len + 1])) {
     const char tag = buf[reader->bprefix_len];
     if (tag == 'b') {
-      buf[reader->bprefix_len] = 'B'; // Prevent clash
+      // Presumably generated ID like b123 in the input, adjust to B123
+      buf[reader->bprefix_len] = 'B';
       reader->seen_genid       = true;
     } else if (tag == 'B' && reader->seen_genid) {
+      // We've seen both b123 and B123 styles, abort due to possible clashes
       return r_err(reader,
                    SERD_BAD_LABEL,
                    "found both 'b' and 'B' blank IDs, prefix required");
diff --git a/test/meson.build b/test/meson.build
index 84ae7525..0092af4b 100644
--- a/test/meson.build
+++ b/test/meson.build
@@ -504,6 +504,7 @@ test_suites = {
     files('extra/prefix/manifest.ttl'),
     ns_serdtest + 'prefix/',
     '--',
+    ['-I', 'generated'],
     ['-p', 'test'],
   ],
   'prefix_remove': [
diff --git a/tools/console.c b/tools/console.c
index 56464696..1a2cb46c 100644
--- a/tools/console.c
+++ b/tools/console.c
@@ -99,6 +99,7 @@ serd_set_input_option(const SerdStringView   name,
     {"lax", SERD_READ_LAX},
     {"variables", SERD_READ_VARIABLES},
     {"verbatim", SERD_READ_VERBATIM},
+    {"generated", SERD_READ_GENERATED},
     {NULL, SERD_READ_LAX},
   };