Merge branch 'master' of github.com:marbl/canu

documentation/source/faq.rst

@@ -105,6 +105,18 @@ What parameters should I use for my reads?
        coverage. 
 
 
+Can I assemble RNA sequence data?
+-------------------------------------
+    Canu will likely mis-assemble, or completely fail to assemble, RNA data.  It will do a
+    reasonable job at generating corrected reads though.  Reads are corrected using (local) best
+    alignments to other reads, and alignments between different isoforms are usually obviously not
+    'best'.  Just like with DNA sequences, similar isoforms can get 'mixed' together.  We've heard
+    of reasonable success from users, but do not have any parameter suggestions to make.
+
+    Note that Canu will silently translate 'U' bases to 'T' bases on input, but **NOT** translate
+    the output bases back to 'U'.
+
+
 My assembly continuity is not good, how can I improve it?
 -------------------------------------
     The most important determinant for assembly quality is sequence length, followed by the repeat

documentation/source/parameter-reference.rst

@@ -124,10 +124,44 @@ onFailure <string=unset>
 Process Control
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
+.. _showNext:
+
 showNext <boolean=false>
   Report the first major command that would be run, but don't run it.  Processing to get to that
-  command, for example, checking the output of the previous command or preparing inputs for the
-  next command, is still performed.
+  command, for example, checking the output of the previous command or preparing inputs for the next
+  command, is still performed.
+
+.. _stopOnReadQuality:
+
+stopOnReadQuality <string=true>
+  If set, Canu will stop with the following error if there are significantly fewer reads or bases
+  loaded into the read store than what is in the input data.
+
+  ::
+
+   Gatekeeper detected potential problems in your input reads.
+   
+   Please review the logging in files:
+     /assembly/godzilla/asm.gkpStore.BUILDING.err
+     /assembly/godzilla/asm.gkpStore.BUILDING/errorLog
+   
+   If you wish to proceed, rename the store with the following command and restart canu.
+   
+     mv /assembly/godzilla/asm.gkpStore.BUILDING \
+        /assembly/godzilla/asm.gkpStore.ACCEPTED
+   
+   Option stopOnReadQuality=false skips these checks.
+
+  The missing reads could be too short (decrease :ref:`minReadLength <minReadLength>` to include
+  them), or have invalid bases or quality values.  A summary of the files loaded and errors detected
+  is in the ``asm.gkpStore.BUILDING.err`` file, with full gory details in the
+  ``asm.gkpStore.BUILDING/errorLog``.
+
+  To proceed, set ``stopOnReadQuality=false`` or rename the directory as shown.
+
+  Note that `U` bases are silently translated to `T` bases, to allow assembly of RNA sequences.
+
+.. _stopAfter:
 
 stopAfter <string=undefined>
   If set, Canu will stop processing after a specific stage in the pipeline finishes.

src/AS_UTL/AS_UTL_decodeRange.H

@@ -38,115 +38,65 @@
 using namespace std;
 
 
-
-template<typename T>
-class AS_UTL_range {
-public:
-  AS_UTL_range() {
-  };
-  AS_UTL_range(T bgn, T end) {
-  }
-
-  bool  operator<(const AS_UTL_range<T> &that) const {
-    if (_bgn < that._bgn)
-      return(true);
-    return(_end < that._end);
-  };
-
-private:
-  T  _bgn;
-  T  _end;
-};
-
-
-
 template<typename T>
-void
-AS_UTL_decodeRange(char *range, vector< AS_UTL_range<T> > &ranges) {
+char *
+AS_UTL_decodeRange(char *range, T &lo, T &hi) {
   char    *ap = range;
-  T        av = 0;
-  T        bv = 0;
 
-  while (*ap != 0) {
-    strtonumber(av, ap, &ap);
+  strtonumber(lo, ap, &ap);     //  Grab the first number.
+
+  hi = lo;                      //  Set the second to that.
 
-    if (*ap == ',') {
-      ap++;
-      ranges.insert(av);
+  if (*ap == '-') {             //  If this is a range,
+    ap++;                       //  grab the second number
+    strtonumber(hi, ap, &ap);
+  }
 
-    } else if (*ap == 0) {
-      ranges.insert(av);
+  if (*ap == ',')               //  If the next letter continues
+    return(ap + 1);             //  move past that and return.
 
-    } else if (*ap == '-') {
-      ap++;
-      strtonumber(bv, ap, &ap);
+  if (*ap == 0)                 //  If the next letter is the end
+    return(NULL);               //  of the string, return NULL.
 
-      for (T xx=av; xx<=bv; xx++)
-        ranges.insert(xx);
+  //  Otherwise, we can't decode this range.
 
-      if (*ap == ',')
-        ap++;
+  fprintf(stderr, "ERROR: invalid range '%s'\n", range);
+  exit(1);
 
-    } else if (*ap != 0) {
-      fprintf(stderr, "ERROR: invalid range '%s'\n", range);
-      exit(1);
-    }
-  }
+  return(NULL);
 }
 
 
 
 template<typename T>
 void
-AS_UTL_decodeRange(char *range, set<T> &ranges) {
+AS_UTL_decodeRange(char *range, vector<T> &bgn, vector<T> &end) {
   char    *ap = range;
   T        av = 0;
   T        bv = 0;
 
-  while (*ap != 0) {
-    strtonumber(av, ap, &ap);
-
-    if (*ap == ',') {
-      ap++;
-      ranges.insert(av);
-
-    } else if (*ap == 0) {
-      ranges.insert(av);
-
-    } else if (*ap == '-') {
-      ap++;
-      strtonumber(bv, ap, &ap);
-
-      for (T xx=av; xx<=bv; xx++)
-        ranges.insert(xx);
+  while ((ap != NULL) && (*ap != 0)) {
+    range = AS_UTL_decodeRange(range, av, bv);
 
-      if (*ap == ',')
-        ap++;
-
-    } else if (*ap != 0) {
-      fprintf(stderr, "ERROR: invalid range '%s'\n", range);
-      exit(1);
-    }
+    bgn.push_back(av);
+    end.push_back(bv);
   }
 }
 
 
 
 template<typename T>
 void
-AS_UTL_decodeRange(char *range, T &lo, T &hi) {
+AS_UTL_decodeRange(char *range, set<T> &ranges) {
   char    *ap = range;
+  T        av = 0;
+  T        bv = 0;
 
-  strtonumber(lo, ap, &ap);
-  hi = lo;
-
-  if (*ap == '-') {
-    ap++;
-    strtonumber(hi, ap, &ap);
+  while ((ap != NULL) && (*ap != 0)) {
+    range = AS_UTL_decodeRange(range, av, bv);
 
-  } else if (*ap != 0) {
-    fprintf(stderr, "ERROR: invalid range '%s'\n", range);
-    exit(1);
+    for (T xx=av; xx<=bv; xx++)
+      ranges.insert(xx);
   }
 }