Initial commit

1 files changed, 64 insertions, 0 deletions

diff --git a/src/lib/lexer.mll b/src/lib/lexer.mll
new file mode 100644
index 0000000..236e353
--- /dev/null
+++ b/src/lib/lexer.mll
@@ -0,0 +1,64 @@
+{
+
+ open Tokens
+
+ exception Error of string
+
+}
+
+rule letter = parse
+| '|'           { Sep }
+| 'a'           { A }
+| 'b'           { B }
+| 'c'           { C }
+| 'd'           { D }
+| 'e'           { E }
+| '\233'        { E_ACUTE }
+| '\xC3' '\xA9' { E_ACUTE }
+| 'f'           { F }
+| 'g'           { G }
+| "gu"          { G }
+| 'h'           { H }
+| 'i'           { I }
+| 'j'           { J }
+| 'k'           { K }
+| 'l'           { L }
+| 'm'           { M }
+| "mm"          { M }
+| 'n'           { N }
+| "nn"          { N }
+| 'o'           { O }
+| 'p'           { P }
+| "ph"          { F }
+| 'q'           { Q }
+| "qu"          { K }
+| 'r'           { R }
+| 'u'           { U }
+| 's'           { S }
+| "ss"          { SS }
+| 't'           { T }
+| 'u'           { U }
+| 'v'           { V }
+| 'w'           { W }
+| 'x'           { X }
+| 'y'           { Y }
+| 'z'           { Z }
+| ' '           { Space }
+| '\n'          { EOL }
+| eof           { EOL }
+
+(* This rule looks for a single line, terminated with '\n' or eof.
+   It returns a pair of an optional string (the line that was found)
+   and a Boolean flag (false if eof was reached). *)
+
+and line = parse
+| ([^'\n']* '\n') as line
+    (* Normal case: one line, no eof. *)
+    { Some line, true }
+| eof
+    (* Normal case: no data, eof. *)
+    { None, false }
+| ([^'\n']+ as line) eof
+    (* Special case: some data but missing '\n', then eof.
+       Consider this as the last line, and add the missing '\n'. *)
+    { Some (line), false }