paste() / nchar() / substr() (String Operations)

# -----------------------------------------------
# paste() — concatenate strings
# -----------------------------------------------

# sep specifies the separator (default is " ", a single space)
paste(..., sep = " ")

# collapse joins all elements of a vector into one string
paste(..., sep = " ", collapse = NULL)

# paste0() is shorthand for sep = "" (no separator)
paste0(..., collapse = NULL)

# -----------------------------------------------
# nchar() — return the number of characters
# -----------------------------------------------

nchar(x)                        # Returns the number of characters in string x
nchar(x, type = "chars")        # type = "chars": character count (default)
nchar(x, type = "bytes")        # type = "bytes": byte count
nchar(x, allowNA = TRUE)        # Allows NA in the result (default is FALSE)

# -----------------------------------------------
# substr() — extract or replace a substring
# -----------------------------------------------

substr(x, start, stop)          # Returns characters from position start to stop in x
substr(x, start, stop) <- value # Replaces the specified range with value (destructive)

# substring() defaults stop to the end of the string (nchar(x))
substring(x, first, last = 1000000L)

psychopass_string_basic.R

# psychopass_string_basic.R — sample for paste() / nchar() / substr()
# Uses PSYCHO-PASS character data
# to explore string concatenation, character counts, and substring operations

# -----------------------------------------------
# Concatenation with paste()
# -----------------------------------------------

# Define character names and titles as separate vectors
names   <- c("Tsunemori Akane", "Ginoza Nobuchika", "Kogami Shinya", "Kagari Shusei", "Shimomura Mika")
titles  <- c("Inspector", "Inspector", "Enforcer", "Enforcer", "Inspector")

cat("--- paste(): concatenate name and title (sep = \": \") ---\n")
labels <- paste(names, titles, sep = ": ")
print(labels)
cat("\n")

# -----------------------------------------------
# No-separator concatenation with paste0()
# -----------------------------------------------

cat("--- paste0(): build a department name ---\n")
bureau   <- "PublicSafetyBureau"
division <- "CriminalInvestigation"
unit     <- "Div1"

full_unit <- paste0(bureau, "-", division, "-", unit)
cat("Department:", full_unit, "\n\n")

# -----------------------------------------------
# Collapsing a vector into one string with collapse
# -----------------------------------------------

cat("--- collapse: join all elements into one string ---\n")
all_names <- paste(names, collapse = " / ")
cat("All characters:", all_names, "\n\n")

# -----------------------------------------------
# Getting character counts with nchar()
# -----------------------------------------------

cat("--- nchar(): get character count for each name ---\n")
char_counts <- nchar(names)

for (i in seq_along(names)) {
  cat(sprintf("  %s -> %d characters\n", names[i], char_counts[i]))
}
cat("\n")

# -----------------------------------------------
# Comparing type = "chars" vs type = "bytes" with nchar()
# -----------------------------------------------

cat("--- nchar() type comparison ---\n")
sample_name <- "Tsunemori Akane"

chars_count <- nchar(sample_name, type = "chars")
bytes_count <- nchar(sample_name, type = "bytes")

cat(sprintf("  \"%s\"  chars: %d  bytes: %d\n", sample_name, chars_count, bytes_count))
cat("\n")

# -----------------------------------------------
# Extracting a substring with substr()
# -----------------------------------------------

cat("--- substr(): extract the first name (last word) ---\n")
for (name in names) {
  parts      <- strsplit(name, " ", fixed = TRUE)[[1]]
  first_name <- parts[length(parts)]
  cat(sprintf("  %s -> given name: %s\n", name, first_name))
}
cat("\n")

# -----------------------------------------------
# Replacing a range with substr()
# -----------------------------------------------

cat("--- substr(): replace a portion of the string ---\n")
code_name <- "Inspector: Tsunemori Akane"
cat("Original:", code_name, "\n")

substr(code_name, 1, 9) <- "Enforcer "
cat("Replaced:", code_name, "\n\n")

# -----------------------------------------------
# Extracting to the end with substring()
# -----------------------------------------------

cat("--- substring(): omit stop to extract to end ---\n")
record <- "CC: Tsunemori Akane: 67.4"

extracted <- substring(record, 5)
cat("Original:", record, "\n")
cat("From position 5:", extracted, "\n\n")

# -----------------------------------------------
# Practical example: filter by name length
# -----------------------------------------------

cat("--- Filter characters with 12 or more characters in their name ---\n")
long_names <- names[nchar(names) >= 12]
cat(paste(long_names, collapse = ", "), "\n")

Rscript psychopass_string_basic.R
--- paste(): concatenate name and title (sep = ": ") ---
[1] "Tsunemori Akane: Inspector"   "Ginoza Nobuchika: Inspector"
[3] "Kogami Shinya: Enforcer"      "Kagari Shusei: Enforcer"
[5] "Shimomura Mika: Inspector"

--- paste0(): build a department name ---
Department: PublicSafetyBureau-CriminalInvestigation-Div1

--- collapse: join all elements into one string ---
All characters: Tsunemori Akane / Ginoza Nobuchika / Kogami Shinya / Kagari Shusei / Shimomura Mika

--- nchar(): get character count for each name ---
  Tsunemori Akane -> 15 characters
  Ginoza Nobuchika -> 16 characters
  Kogami Shinya -> 13 characters
  Kagari Shusei -> 13 characters
  Shimomura Mika -> 14 characters

--- nchar() type comparison ---
  "Tsunemori Akane"  chars: 15  bytes: 15

--- substr(): extract the first name (last word) ---
  Tsunemori Akane -> given name: Akane
  Ginoza Nobuchika -> given name: Nobuchika
  Kogami Shinya -> given name: Shinya
  Kagari Shusei -> given name: Shusei
  Shimomura Mika -> given name: Mika

--- substr(): replace a portion of the string ---
Original: Inspector: Tsunemori Akane
Replaced: Enforcer  Tsunemori Akane

--- substring(): omit stop to extract to end ---
Original: CC: Tsunemori Akane: 67.4
From position 5: Tsunemori Akane: 67.4

--- Filter characters with 12 or more characters in their name ---
Tsunemori Akane, Ginoza Nobuchika, Kogami Shinya, Kagari Shusei, Shimomura Mika

1: nchar() returns character count, not byte count

The default for nchar() is type = "chars", which counts each character as one unit even for multi-byte characters. For ASCII strings, character count and byte count are the same. When byte count is needed, specify type = "bytes".

string_nchar_bytes.R

name_ascii <- "Akane"

# type = "chars" (default): counts characters
cat(sprintf("chars: %d\n", nchar(name_ascii, type = "chars")))

# type = "bytes": counts bytes (same for ASCII; differs for multi-byte)
cat(sprintf("bytes: %d\n", nchar(name_ascii, type = "bytes")))

chars: 5
bytes: 5

2: The default sep in paste() is a space, not an empty string

The default value of sep in paste() is " " (a single space). If you want to concatenate without a separator and omit sep, a space will be inserted between elements. Use paste0() or paste(..., sep = "") for no-separator concatenation. The collapse argument (shared by both paste() and paste0()) folds a vector into a single string.

string_paste_sep.R

bureau   <- "PublicSafety"
division <- "Criminal"
unit     <- "Div1"

# paste() default sep is " " (space)
cat(paste(bureau, division, unit), "\n")

# Use paste0() for no-separator concatenation
cat(paste0(bureau, division, unit), "\n")

# Explicitly specifying sep = "" gives the same result
cat(paste(bureau, division, unit, sep = ""), "\n")

# collapse folds a vector into a single string
names <- c("Akane", "Nobuchika", "Shinya")
cat(paste(names, collapse = " / "), "\n")

PublicSafety Criminal Div1
PublicSafetyCriminalDiv1
PublicSafetyCriminalDiv1
Akane / Nobuchika / Shinya

R's paste() concatenates multiple strings using the separator specified by sep, and collapses an entire vector into one string using collapse. paste0() is a shorthand for sep = "", convenient for no-separator concatenation. nchar() returns the character count (or byte count with type = "bytes") and is vectorized, so the counts for all elements of a character vector can be obtained at once. substr(x, start, stop) uses 1-based indexing to extract a substring; used on the left-hand side, it replaces the specified range. When you want to omit stop, use substring() to extract from a position to the end of the string. For string search and replacement, see grep() / sub() / gsub(). For formatted output, see sprintf().