minorfix

telatin · Jun 5, 2022 · f289eaa · f289eaa
1 parent df40240
commit f289eaa
Show file tree

Hide file tree

Showing 4 changed files with 43 additions and 29 deletions.
diff --git a/src/fastx_stats.nim b/src/fastx_stats.nim
@@ -89,7 +89,19 @@ Sample	col1	col2	col3	col4	col5	col6	col7  col8  col9
   let
     outputTable = newUnicodeTable()
     headerFields = @["File", "#Seq", "Total bp","Avg", "N50", "N75", "N90", "auN", "Min", "Max"]
-
+  var
+    opt : statsOptions = (
+      absolute: bool(args["--abs-path"]),
+      basename: bool(args["--basename"]),
+      precision: 2,
+      thousands: false,
+      header: true,
+      gc: false,
+      scaffolds: false,
+      delim: sep,
+      fields: @[]
+    )
+
   if nice:
     outputTable.separateRows = false
     outputTable.setHeaders(headerFields)
@@ -102,7 +114,7 @@ Sample	col1	col2	col3	col4	col5	col6	col7  col8  col9
       continue
 
     var
-      stats = getFastxStats(filename)
+      stats = getFastxStats(filename, opt)
 
     var rendername = if printBasename: $getBasename(filename)
       else: filename

diff --git a/src/fastx_stats2.nim b/src/fastx_stats2.nim
@@ -7,19 +7,6 @@ import ./seqfu_utils
 import ./stats_utils 
 import algorithm
 
-type
-  statsOptions = tuple[
-    absolute: bool,
-    basename: bool,
-    precision: int,
-    thousands: bool,
-    header: bool, 
-    gc: bool, 
-    scaffolds: bool, 
-    delim: string, 
-    fields: seq[string]
-  ]
-
 
 proc toSequence(s: FastxStats, o: statsOptions): seq[string] =
   var
@@ -210,7 +197,7 @@ Sample	col1	col2	col3	col4	col5	col6	col7	col8	col9	col10
       continue
 
     var
-      stats = getFastxStats(filename)
+      stats = getFastxStats(filename, opt)
 
     if printBasename:
       stats.filename = getBasename(stats.filename)

diff --git a/src/stats_utils.nim b/src/stats_utils.nim
@@ -8,6 +8,19 @@ import seqfu_utils
 type
   FastxStats*   = tuple[filename: string, count, sum, min, max, n25, n50, n75, n90: int, gc, auN, avg: float]
 
+type
+  statsOptions* = tuple[
+    absolute: bool,
+    basename: bool,
+    precision: int,
+    thousands: bool,
+    header: bool, 
+    gc: bool, 
+    scaffolds: bool, 
+    delim: string, 
+    fields: seq[string]
+  ]
+
 proc toTable*(s: FastxStats): Table[string, string] =
   result["Filename"] = s.filename
   result["Total"] = $s.sum
@@ -22,7 +35,7 @@ proc toTable*(s: FastxStats): Table[string, string] =
   result["AuN"] = $s.auN
   result["gc"] = $s.gc
 
-proc getFastxStats*(filename: string): FastxStats {.discardable.} =
+proc getFastxStats*(filename: string, o: statsOptions): FastxStats {.discardable.} =
   result.filename = filename
   var
     totalBases = 0
@@ -37,9 +50,11 @@ proc getFastxStats*(filename: string): FastxStats {.discardable.} =
   try:
     for r in readfq(filename):
       var ctgLen = len(r.sequence)
-      let nucleotides = count_all(r.sequence)
-      gc += nucleotides.gc
-      realLen += nucleotides.tot
+      if o.gc:
+        let nucleotides = count_all(r.sequence)
+        gc += nucleotides.gc
+        realLen += nucleotides.tot
+
       if not (ctgLen in ctgSizes):
         ctgSizes[ctgLen] = 1
       else:

diff --git a/test/test-stats.sh b/test/test-stats.sh
@@ -2,14 +2,14 @@
 
 # Single file
 TMP=$(mktemp)
-STATS=$("$BINDIR"/seqfu stats --basename $iAmpli > $TMP)
+STATS=$("$BINDIR"/seqfu stats --basename "$iAmpli" > "$TMP")
 
 WC=$(cat "$TMP" | wc -l | grep -o '\d\+')
 SEQS=$(cat "$TMP" | tail -n 1 | cut -f 2)
 TOT=$(cat "$TMP" | tail -n 1 | cut -f 3)
 N50=$(cat "$TMP" | tail -n 1 | cut -f 5)
 
-MSG="Checking normal output expecting 2 lines: <$WC>"
+MSG="Checking normal output expecting 2 lines: <"$WC">"
 if [[ $WC == 2 ]]; then
     echo -e "$OK: $MSG"
     PASS=$((PASS+1))
@@ -20,7 +20,7 @@ fi
 
 
 MSG="Checking normal output expecting total seqs 78730: <$SEQS>"
-if [[ $SEQS == 78730 ]]; then
+if [[ "$SEQS" == 78730 ]]; then
     echo -e "$OK: $MSG"
     PASS=$((PASS+1))
 else
@@ -29,7 +29,7 @@ else
 fi
 
 MSG="Checking normal output expecting total bases 24299931: <$TOT>"
-if [[ $TOT == 24299931 ]]; then
+if [[ "$TOT" == 24299931 ]]; then
     echo -e "$OK: $MSG"
     PASS=$((PASS+1))
 else
@@ -60,7 +60,7 @@ fi
 # Nice output
 STATS=$("$BINDIR"/seqfu stats --basename --nice $iAmpli > $TMP)
 WC=$(cat "$TMP" | grep . | wc -l | grep -o '\d\+')
-if [[ $WC == 5 ]]; then
+if [[ "$WC" == 5 ]]; then
     echo -e "$OK: Checking nice output expecting 5 lines: <$WC>"
     PASS=$((PASS+1))
 else
@@ -70,10 +70,10 @@ fi
 
 # Json 
 TMP2=$(mktemp)
-STATS=$("$BINDIR"/seqfu stats --basename --json --multiqc $TMP2 $iAmpli > $TMP)
+STATS=$("$BINDIR"/seqfu stats --basename --json --multiqc "$TMP2" "$iAmpli" > "$TMP")
 WC=$(cat "$TMP" | grep . | wc -l | grep -o '\d\+')
 WC2=$(cat "$TMP2" | grep . | wc -l | grep -o '\d\+')
-if [[ $WC2 == 39 ]]; then
+if [[ "$WC2" == 39 ]]; then
     echo -e "$OK: Checking MultiQC output expecting 39 lines: <$WC2>"
     PASS=$((PASS+1))
 else
@@ -91,9 +91,9 @@ fi
 # Multi file 
 
 # Default sort
-"$BINDIR"/seqfu stats --basename  $iAmpli $iSort $iMini > $TMP
+"$BINDIR"/seqfu stats --basename  "$iAmpli" "$iSort" "$iMini" > "$TMP"
 # Sort by N50 descending
-"$BINDIR"/seqfu stats --basename  --sort n50 --reverse $iAmpli $iSort $iMini > $TMP2
+"$BINDIR"/seqfu stats --basename  --sort n50 --reverse  "$iAmpli" "$iSort" "$iMini" > "$TMP2"
 
 FILT=$(cat $TMP | head -n 2 | tail -n 1 | cut -f 1)
 MSG="Checking default starting  by 'filt': <$FILT>"