Parsing a text file by a delimiter and outputting multiple files with R

Probably using some UNIX commands would be most "natural", awk and csplit would work in that regard.

I have an R solution for you anyways. Instead of using readLines() I would start with read.delim(). That way you start out with a data.frame and can then use any tools for data.frame manipulation. I am most familiar with the tidyverse commands, that's why I would use them here.

# Process File 
library(tidyverse)
log_df <- read.delim(serverLog, header = FALSE) %>% 
  mutate(breakpoint = grepl("Monthly Breakpoint", V1),
         breakdate = ifelse(breakpoint, gsub("Monthly Breakpoint, ", "", V1), NA)) %>% 
  fill(breakdate) %>% 
  mutate(breakdate = ifelse(is.na(breakdate), "before first breakdate", breakdate)) %>% 
  filter(!breakpoint) %>% 
  select(-breakpoint)

# Save Files
log_df %>% 
  split(.$breakdate) %>% 
  lapply(function(x) write.csv(x, file = paste(x$breakdate[1], ".csv"), row.names = FALSE))

I don't know though, if storing the data in separate files is the best workflow to choose here. Why not just keep the data in R, split up the lines in several columns and group your analysis by months.

EDIT: This is what the splitting into columns and some analysis could look like.

# split / separate() into columns

log_sep_df <- 
  log_df %>%
  as_tibble() %>% 
  mutate(V1 = substr(V1, 2, nchar(as.character(V1)))) %>% 
  separate(V1, into = c(paste0("var", 1:10)), sep = "\\[|  | ") %>% 
  mutate(http = ifelse(grepl("POST", var1), "POST", "GET")) %>% 
  mutate(var1 = gsub("POST|GET", "", var1))

# get month labels
library(lubridate)
log_sep_df <- 
log_sep_df %>% 
  mutate(date = as.Date(mdy(log_sep_df$breakdate)))

date_before_first_breakpoint <- min(log_sep_df$date, na.rm = TRUE) - 10

log_sep_df <- 
log_sep_df %>% 
  mutate(date = if_else(is.na(date), 
                        date_before_first_breakpoint, 
                        date),
         month = month(date, label = TRUE))


# grouped visiualization of logs
ggplot(log_sep_df, aes(http)) +
  geom_bar() +
  facet_wrap(~month)

This isn't the most elegant answer but this got me what I needed. I'll try out the other answer, it's a good idea to keep the data in my R environment so I can run all my metrics without reading in unnecessary files. Thanks @Till

#~~~~~~~~~~~~~~~~~~~~~~#
#~~ Parse Server Log ~~#
#~~~~~~~~~~~~~~~~~~~~~~#

# Read File 
serverLog <- "server-out.min"
conn <- file( serverLog ,open="r")
linn <-readLines(conn)
num <- 1

# Loop through File 
for (i in 1:length(linn)){
  # print( linn[i] )

  # current output file
  file <- paste( "server-log-", num, sep = "")
  # write to file
  write(linn[i], file=file, append=TRUE)

  # Check for Monthly Delimiter, update num
  test <- grepl(  "Monthly", linn[i] )
  if( test ) {
    print( "Found Monthly Breakpoint")
    num <- num+1
  }
}
close(conn)

If you want to do it in R, you could use a data.table solution for efficiency:

library(data.table)
DT <- fread("out.log", sep = NULL, header = FALSE)[V1 != ""]
DT[, Idx := rleid(grepl("Monthly Breakpoint", V1))]
DT <- DT[!grepl("Monthly Breakpoint", V1)]
DT.list <- split(DT, DT$Idx) ## or just operate by Idx