perf(pest): simplify grammar, remove unnecessary lookaheads

Author: lalvarezt

src/pipeline/template.pest

@@ -39,7 +39,7 @@ shorthand_range = {
   | range_full
 }
 
-// Order of operations matter
+// Main operations - using specific arg types where needed
 regex_extract = { "regex_extract" ~ ":" ~ regex_arg ~ (":" ~ number)? }
 filter_not    = { "filter_not" ~ ":" ~ regex_arg }
 filter        = { "filter" ~ ":" ~ regex_arg }
@@ -48,13 +48,13 @@ map           = { "map" ~ ":" ~ map_operation }
 split         = { "split" ~ ":" ~ split_arg ~ ":" ~ range_spec? }
 substring     = { "substring" ~ ":" ~ range_spec }
 replace       = { "replace" ~ ":" ~ sed_string }
-append        = { "append" ~ ":" ~ arg }
-prepend       = { "prepend" ~ ":" ~ arg }
+append        = { "append" ~ ":" ~ simple_arg }
+prepend       = { "prepend" ~ ":" ~ simple_arg }
 upper         = { "upper" }
 lower         = { "lower" }
 trim          = { "trim" ~ (":" ~ direction)? }
-strip         = { "strip" ~ ":" ~ arg }
-join          = { "join" ~ ":" ~ arg }
+strip         = { "strip" ~ ":" ~ simple_arg }
+join          = { "join" ~ ":" ~ simple_arg }
 slice         = { "slice" ~ ":" ~ range_spec }
 sort          = { "sort" ~ (":" ~ sort_direction)? }
 reverse       = { "reverse" }
@@ -64,7 +64,7 @@ pad           = { "pad" ~ ":" ~ number ~ (":" ~ pad_char)? ~ (":" ~ direction)?
 // Direction specifiers
 direction      =  { "left" | "right" | "both" }
 sort_direction =  { "asc" | "desc" }
-pad_char       = @{ (escaped_char | normal_char)+ }
+pad_char       = @{ simple_arg_content+ }
 
 // Map operation
 map_operation       = { "{" ~ map_operation_list ~ "}" }
@@ -84,45 +84,35 @@ map_inner_operation = {
   | map_regex_extract
 }
 
-// Map-specific operations that use map_regex_arg
+// Map-specific regex extract
 map_regex_extract = { "regex_extract" ~ ":" ~ map_regex_arg ~ (":" ~ number)? }
 
-// Regular arguments
-arg          = { (escaped_char | normal_char | " " | "\t")* }
-normal_char  = { !(":" | "|" | "}" | "{" | "\\") ~ ANY }
-escaped_char = { "\\" ~ (":" | "|" | "\\" | "n" | "t" | "r" | "/" | "{" | "}") }
-
-// Split arguments - allow pipes unless followed by operation names
-split_arg          = @{ (split_escaped_char | split_pipe_or_char)* }
-split_pipe_or_char =  { split_pipe | split_normal_char }
-split_pipe         =  { "|" ~ !operation_name }
-split_normal_char  =  {
-    !(":" ~ (operation_name | range_spec | number)) ~ !("|" ~ operation_name) ~ !("}" ~ (EOI | !(split_any_char*))) ~ ANY
-}
+// Simplified argument handling - three types to handle specific cases
+simple_arg         = @{ simple_arg_content* }
+simple_arg_content =  { escaped_char | simple_normal_char }
+simple_normal_char =  { !(":" | "|" | "}" | "{" | "\\") ~ ANY }
+
+// Split args - need to handle pipes that aren't operations
+split_arg          = @{ (split_escaped_char | split_content)* }
+split_content      =  { !(":" ~ (number | range_part)) ~ !("|" ~ operation_keyword) ~ !("}" ~ EOI) ~ ANY }
 split_escaped_char =  { "\\" ~ ANY }
-split_any_char     =  { ANY }
-
-// Regex arguments - allow pipes unless followed by operation names, and handle braces
-regex_arg          = @{ (regex_escaped_char | regex_pipe_or_char)* }
-regex_pipe_or_char =  { regex_pipe | regex_normal_char }
-regex_pipe         =  { "|" ~ !operation_name }
-regex_normal_char  =  {
-    !(":" ~ (operation_name | range_spec | number)) ~ !("|" ~ operation_name) ~ !("}" ~ (EOI | "|")) ~ ANY
-}
+
+// Regex args - need to handle pipes and braces in regex patterns
+regex_arg          = @{ (regex_escaped_char | regex_content)* }
+regex_content      =  { !(":" ~ (number | range_part)) ~ !("|" ~ operation_keyword) ~ !("}" ~ EOI) ~ ANY }
 regex_escaped_char =  { "\\" ~ ANY }
 
-// Regex arguments for map operations (improved to handle braces in regex)
-map_regex_arg          = @{ (map_regex_escaped_char | map_regex_balanced_brace | map_regex_pipe_or_char)* }
-map_regex_pipe_or_char =  { map_regex_pipe | map_regex_normal_char }
-map_regex_pipe         =  { "|" ~ !operation_name }
-map_regex_balanced_brace = { "{" ~ (!("}" ~ &("|" | "}" | EOI | (":" ~ number))) ~ ANY)* ~ "}" }
-map_regex_normal_char  =  {
-    !(":" ~ (operation_name | range_spec | number)) ~ !("|" ~ operation_name) ~ !("{" | ("}" ~ &("|" | "}" | EOI | (":" ~ number)))) ~ ANY
-}
+// Map regex args - handle braces in regex patterns
+map_regex_arg          = @{ (map_regex_escaped_char | map_regex_brace | map_regex_content)* }
+map_regex_brace        =  { "{" ~ (!"}" ~ ANY)* ~ "}" }
+map_regex_content      =  { !(":" ~ number) ~ !("|" ~ operation_keyword) ~ !("{" | ("}" ~ ("|" | "}" | EOI))) ~ ANY }
 map_regex_escaped_char =  { "\\" ~ ANY }
 
-// Operation names for lookahead
-operation_name = {
+// Common escaped character handling
+escaped_char = { "\\" ~ ANY }
+
+// Operation keywords for lookahead (simplified list)
+operation_keyword = {
     "split"
   | "join"
   | "substring"
@@ -145,7 +135,10 @@ operation_name = {
   | "pad"
 }
 
-// Sed strings (preserve sed/regex escape sequences)
+// Range parts for lookahead
+range_part = { ".." | "..=" }
+
+// Sed strings
 sed_string       =  { "s/" ~ sed_pattern ~ "/" ~ sed_replacement ~ "/" ~ sed_flags? }
 sed_pattern      = @{ sed_content }
 sed_replacement  = @{ sed_content }